Chenggang Yan

Zeqiang Lai, Chenggang Yan, Ying Fu

In this paper, we present a Hybrid Spectral Denoising Transformer (HSDT) for hyperspectral image denoising. Challenges in adapting transformer for HSI arise from the capabilities to tackle existing limitations of CNN-based methods in capturing the global and local spatial-spectral correlations while maintaining efficiency and flexibility. To address these issues, we introduce a hybrid approach that combines the advantages of both models with a Spatial-Spectral Separable Convolution (S3Conv), Guided Spectral Self-Attention (GSSA), and Self-Modulated Feed-Forward Network (SM-FFN). Our S3Conv works as a lightweight alternative to 3D convolution, which extracts more spatial-spectral correlated features while keeping the flexibility to tackle HSIs with an arbitrary number of bands. These features are then adaptively processed by GSSA which per-forms 3D self-attention across the spectral bands, guided by a set of learnable queries that encode the spectral signatures. This not only enriches our model with powerful capabilities for identifying global spectral correlations but also maintains linear complexity. Moreover, our SM-FFN proposes the self-modulation that intensifies the activations of more informative regions, which further strengthens the aggregated features. Extensive experiments are conducted on various datasets under both simulated and real-world noise, and it shows that our HSDT significantly outperforms the existing state-of-the-art methods while maintaining low computational overhead. Code is at https: //github.com/Zeqiang-Lai/HSDT.

Yunbin Tu, Liang Li, Li Su et al.

Change captioning aims to describe the difference between a pair of similar images. Its key challenge is how to learn a stable difference representation under pseudo changes caused by viewpoint change. In this paper, we address this by proposing a self-supervised cross-view representation reconstruction (SCORER) network. Concretely, we first design a multi-head token-wise matching to model relationships between cross-view features from similar/dissimilar images. Then, by maximizing cross-view contrastive alignment of two similar images, SCORER learns two view-invariant image representations in a self-supervised way. Based on these, we reconstruct the representations of unchanged objects by cross-attention, thus learning a stable difference representation for caption generation. Further, we devise a cross-modal backward reasoning to improve the quality of caption. This module reversely models a ``hallucination'' representation with the caption and ``before'' representation. By pushing it closer to the ``after'' representation, we enforce the caption to be informative about the difference in a self-supervised manner. Extensive experiments show our method achieves the state-of-the-art results on four datasets. The code is available at https://github.com/tuyunbin/SCORER.

Linwei Chen, Ying Fu, Lin Gu et al.

Dense image prediction tasks demand features with strong category information and precise spatial boundary details at high resolution. To achieve this, modern hierarchical models often utilize feature fusion, directly adding upsampled coarse features from deep layers and high-resolution features from lower levels. In this paper, we observe rapid variations in fused feature values within objects, resulting in intra-category inconsistency due to disturbed high-frequency features. Additionally, blurred boundaries in fused features lack accurate high frequency, leading to boundary displacement. Building upon these observations, we propose Frequency-Aware Feature Fusion (FreqFusion), integrating an Adaptive Low-Pass Filter (ALPF) generator, an offset generator, and an Adaptive High-Pass Filter (AHPF) generator. The ALPF generator predicts spatially-variant low-pass filters to attenuate high-frequency components within objects, reducing intra-class inconsistency during upsampling. The offset generator refines large inconsistent features and thin boundaries by replacing inconsistent features with more consistent ones through resampling, while the AHPF generator enhances high-frequency detailed boundary information lost during downsampling. Comprehensive visualization and quantitative analysis demonstrate that FreqFusion effectively improves feature consistency and sharpens object boundaries. Extensive experiments across various dense prediction tasks confirm its effectiveness. The code is made publicly available at https://github.com/Linwei-Chen/FreqFusion.

Tingyu Wang, Zhedong Zheng, Yaoqi Sun et al.

Aerial-view geo-localization tends to determine an unknown position through matching the drone-view image with the geo-tagged satellite-view image. This task is mostly regarded as an image retrieval problem. The key underpinning this task is to design a series of deep neural networks to learn discriminative image descriptors. However, existing methods meet large performance drops under realistic weather, such as rain and fog, since they do not take the domain shift between the training data and multiple test environments into consideration. To minor this domain gap, we propose a Multiple-environment Self-adaptive Network (MuSe-Net) to dynamically adjust the domain shift caused by environmental changing. In particular, MuSe-Net employs a two-branch neural network containing one multiple-environment style extraction network and one self-adaptive feature extraction network. As the name implies, the multiple-environment style extraction network is to extract the environment-related style information, while the self-adaptive feature extraction network utilizes an adaptive modulation module to dynamically minimize the environment-related style gap. Extensive experiments on two widely-used benchmarks, i.e., University-1652 and CVUSA, demonstrate that the proposed MuSe-Net achieves a competitive result for geo-localization in multiple environments. Furthermore, we observe that the proposed method also shows great potential to the unseen extreme weather, such as mixing the fog, rain and snow.

Yunbin Tu, Liang Li, Li Su et al.

Change captioning aims to succinctly describe the semantic change between a pair of similar images, while being immune to distractors (illumination and viewpoint changes). Under these distractors, unchanged objects often appear pseudo changes about location and scale, and certain objects might overlap others, resulting in perturbational and discrimination-degraded features between two images. However, most existing methods directly capture the difference between them, which risk obtaining error-prone difference features. In this paper, we propose a distractors-immune representation learning network that correlates the corresponding channels of two image representations and decorrelates different ones in a self-supervised manner, thus attaining a pair of stable image representations under distractors. Then, the model can better interact them to capture the reliable difference features for caption generation. To yield words based on the most related difference features, we further design a cross-modal contrastive regularization, which regularizes the cross-modal alignment by maximizing the contrastive alignment between the attended difference features and generated words. Extensive experiments show that our method outperforms the state-of-the-art methods on four public datasets. The code is available at https://github.com/tuyunbin/DIRL.

Jinkai Zheng, Xinchen Liu, Wu Liu et al.

Existing studies for gait recognition are dominated by 2D representations like the silhouette or skeleton of the human body in constrained scenes. However, humans live and walk in the unconstrained 3D space, so projecting the 3D human body onto the 2D plane will discard a lot of crucial information like the viewpoint, shape, and dynamics for gait recognition. Therefore, this paper aims to explore dense 3D representations for gait recognition in the wild, which is a practical yet neglected problem. In particular, we propose a novel framework to explore the 3D Skinned Multi-Person Linear (SMPL) model of the human body for gait recognition, named SMPLGait. Our framework has two elaborately-designed branches of which one extracts appearance features from silhouettes, the other learns knowledge of 3D viewpoints and shapes from the 3D SMPL model. In addition, due to the lack of suitable datasets, we build the first large-scale 3D representation-based gait recognition dataset, named Gait3D. It contains 4,000 subjects and over 25,000 sequences extracted from 39 cameras in an unconstrained indoor scene. More importantly, it provides 3D SMPL models recovered from video frames which can provide dense 3D information of body shape, viewpoint, and dynamics. Based on Gait3D, we comprehensively compare our method with existing gait recognition approaches, which reflects the superior performance of our framework and the potential of 3D representations for gait recognition in the wild. The code and dataset are available at https://gait3d.github.io.

Jinkai Zheng, Xinchen Liu, Xiaoyan Gu et al.

Existing studies for gait recognition are dominated by in-the-lab scenarios. Since people live in real-world senses, gait recognition in the wild is a more practical problem that has recently attracted the attention of the community of multimedia and computer vision. Current methods that obtain state-of-the-art performance on in-the-lab benchmarks achieve much worse accuracy on the recently proposed in-the-wild datasets because these methods can hardly model the varied temporal dynamics of gait sequences in unconstrained scenes. Therefore, this paper presents a novel multi-hop temporal switch method to achieve effective temporal modeling of gait patterns in real-world scenes. Concretely, we design a novel gait recognition network, named Multi-hop Temporal Switch Network (MTSGait), to learn spatial features and multi-scale temporal features simultaneously. Different from existing methods that use 3D convolutions for temporal modeling, our MTSGait models the temporal dynamics of gait sequences by 2D convolutions. By this means, it achieves high efficiency with fewer model parameters and reduces the difficulty in optimization compared with 3D convolution-based models. Based on the specific design of the 2D convolution kernels, our method can eliminate the misalignment of features among adjacent frames. In addition, a new sampling strategy, i.e., non-cyclic continuous sampling, is proposed to make the model learn more robust temporal features. Finally, the proposed method achieves superior performance on two public gait in-the-wild datasets, i.e., GREW and Gait3D, compared with state-of-the-art methods.

Shancheng Fang, Zhendong Mao, Hongtao Xie et al.

Scene text spotting is of great importance to the computer vision community due to its wide variety of applications. Recent methods attempt to introduce linguistic knowledge for challenging recognition rather than pure visual classification. However, how to effectively model the linguistic rules in end-to-end deep networks remains a research challenge. In this paper, we argue that the limited capacity of language models comes from 1) implicit language modeling; 2) unidirectional feature representation; and 3) language model with noise input. Correspondingly, we propose an autonomous, bidirectional and iterative ABINet++ for scene text spotting. Firstly, the autonomous suggests enforcing explicitly language modeling by decoupling the recognizer into vision model and language model and blocking gradient flow between both models. Secondly, a novel bidirectional cloze network (BCN) as the language model is proposed based on bidirectional feature representation. Thirdly, we propose an execution manner of iterative correction for the language model which can effectively alleviate the impact of noise input. Finally, to polish ABINet++ in long text recognition, we propose to aggregate horizontal features by embedding Transformer units inside a U-Net, and design a position and content attention module which integrates character order and content to attend to character features precisely. ABINet++ achieves state-of-the-art performance on both scene text recognition and scene text spotting benchmarks, which consistently demonstrates the superiority of our method in various environments especially on low-quality images. Besides, extensive experiments including in English and Chinese also prove that, a text spotter that incorporates our language modeling method can significantly improve its performance both in accuracy and speed compared with commonly used attention-based recognizers.

Yang Liu, Ersi Zhang, Lulu Xu et al.

Deep learning techniques have shown great potential in medical image processing, particularly through accurate and reliable image segmentation on magnetic resonance imaging (MRI) scans or computed tomography (CT) scans, which allow the localization and diagnosis of lesions. However, training these segmentation models requires a large number of manually annotated pixel-level labels, which are time-consuming and labor-intensive, in contrast to image-level labels that are easier to obtain. It is imperative to resolve this problem through weakly-supervised semantic segmentation models using image-level labels as supervision since it can significantly reduce human annotation efforts. Most of the advanced solutions exploit class activation mapping (CAM). However, the original CAMs rarely capture the precise boundaries of lesions. In this study, we propose the strategy of multi-scale inference to refine CAMs by reducing the detail loss in single-scale reasoning. For segmentation, we develop a novel model named Mixed-UNet, which has two parallel branches in the decoding phase. The results can be obtained after fusing the extracted features from two branches. We evaluate the designed Mixed-UNet against several prevalent deep learning-based segmentation approaches on our dataset collected from the local hospital and public datasets. The validation results demonstrate that our model surpasses available methods under the same supervision level in the segmentation of various lesions from brain imaging.

Chaochao Chen, Jiaming Zhang, Yizhao Zhang et al.

With increasing privacy concerns in artificial intelligence, regulations have mandated the right to be forgotten, granting individuals the right to withdraw their data from models. Machine unlearning has emerged as a potential solution to enable selective forgetting in models, particularly in recommender systems where historical data contains sensitive user information. Despite recent advances in recommendation unlearning, evaluating unlearning methods comprehensively remains challenging due to the absence of a unified evaluation framework and overlooked aspects of deeper influence, e.g., fairness. To address these gaps, we propose CURE4Rec, the first comprehensive benchmark for recommendation unlearning evaluation. CURE4Rec covers four aspects, i.e., unlearning Completeness, recommendation Utility, unleaRning efficiency, and recommendation fairnEss, under three data selection strategies, i.e., core data, edge data, and random data. Specifically, we consider the deeper influence of unlearning on recommendation fairness and robustness towards data with varying impact levels. We construct multiple datasets with CURE4Rec evaluation and conduct extensive experiments on existing recommendation unlearning methods. Our code is released at https://github.com/xiye7lai/CURE4Rec.

Jinkai Zheng, Xinchen Liu, Shuai Wang et al.

Binary silhouettes and keypoint-based skeletons have dominated human gait recognition studies for decades since they are easy to extract from video frames. Despite their success in gait recognition for in-the-lab environments, they usually fail in real-world scenarios due to their low information entropy for gait representations. To achieve accurate gait recognition in the wild, this paper presents a novel gait representation, named Gait Parsing Sequence (GPS). GPSs are sequences of fine-grained human segmentation, i.e., human parsing, extracted from video frames, so they have much higher information entropy to encode the shapes and dynamics of fine-grained human parts during walking. Moreover, to effectively explore the capability of the GPS representation, we propose a novel human parsing-based gait recognition framework, named ParsingGait. ParsingGait contains a Convolutional Neural Network (CNN)-based backbone and two light-weighted heads. The first head extracts global semantic features from GPSs, while the other one learns mutual information of part-level features through Graph Convolutional Networks to model the detailed dynamics of human walking. Furthermore, due to the lack of suitable datasets, we build the first parsing-based dataset for gait recognition in the wild, named Gait3D-Parsing, by extending the large-scale and challenging Gait3D dataset. Based on Gait3D-Parsing, we comprehensively evaluate our method and existing gait recognition methods. The experimental results show a significant improvement in accuracy brought by the GPS representation and the superiority of ParsingGait. The code and dataset are available at https://gait3d.github.io/gait3d-parsing-hp .

Tingyu Wang, Zhedong Zheng, Zunjie Zhu et al.

Cross-view geo-localization aims to spot images of the same location shot from two platforms, e.g., the drone platform and the satellite platform. Existing methods usually focus on optimizing the distance between one embedding with others in the feature space, while neglecting the redundancy of the embedding itself. In this paper, we argue that the low redundancy is also of importance, which motivates the model to mine more diverse patterns. To verify this point, we introduce a simple yet effective regularization, i.e., Dynamic Weighted Decorrelation Regularization (DWDR), to explicitly encourage networks to learn independent embedding channels. As the name implies, DWDR regresses the embedding correlation coefficient matrix to a sparse matrix, i.e., the identity matrix, with dynamic weights. The dynamic weights are applied to focus on still correlated channels during training. Besides, we propose a cross-view symmetric sampling strategy, which keeps the example balance between different platforms. Albeit simple, the proposed method has achieved competitive results on three large-scale benchmarks, i.e., University-1652, CVUSA and CVACT. Moreover, under the harsh circumstance, e.g., the extremely short feature of 64 dimensions, the proposed method surpasses the baseline model by a clear margin.

Hui Song, A. K. Qin, Chenggang Yan

Real-world electricity consumption prediction may involve different tasks, e.g., prediction for different time steps ahead or different geo-locations. These tasks are often solved independently without utilizing some common problem-solving knowledge that could be extracted and shared among these tasks to augment the performance of solving each task. In this work, we propose a multi-task optimization (MTO) based co-training (MTO-CT) framework, where the models for solving different tasks are co-trained via an MTO paradigm in which solving each task may benefit from the knowledge gained from when solving some other tasks to help its solving process. MTO-CT leverages long short-term memory (LSTM) based model as the predictor where the knowledge is represented via connection weights and biases. In MTO-CT, an inter-task knowledge transfer module is designed to transfer knowledge between different tasks, where the most helpful source tasks are selected by using the probability matching and stochastic universal selection, and evolutionary operations like mutation and crossover are performed for reusing the knowledge from selected source tasks in a target task. We use electricity consumption data from five states in Australia to design two sets of tasks at different scales: a) one-step ahead prediction for each state (five tasks) and b) 6-step, 12-step, 18-step, and 24-step ahead prediction for each state (20 tasks). The performance of MTO-CT is evaluated on solving each of these two sets of tasks in comparison to solving each task in the set independently without knowledge sharing under the same settings, which demonstrates the superiority of MTO-CT in terms of prediction accuracy.

Yunhao Zou, Chenggang Yan, Ying Fu

High dynamic range (HDR) images capture much more intensity levels than standard ones. Current methods predominantly generate HDR images from 8-bit low dynamic range (LDR) sRGB images that have been degraded by the camera processing pipeline. However, it becomes a formidable task to retrieve extremely high dynamic range scenes from such limited bit-depth data. Unlike existing methods, the core idea of this work is to incorporate more informative Raw sensor data to generate HDR images, aiming to recover scene information in hard regions (the darkest and brightest areas of an HDR scene). To this end, we propose a model tailor-made for Raw images, harnessing the unique features of Raw data to facilitate the Raw-to-HDR mapping. Specifically, we learn exposure masks to separate the hard and easy regions of a high dynamic scene. Then, we introduce two important guidances, dual intensity guidance, which guides less informative channels with more informative ones, and global spatial guidance, which extrapolates scene specifics over an extended spatial domain. To verify our Raw-to-HDR approach, we collect a large Raw/HDR paired dataset for both training and testing. Our empirical evaluations validate the superiority of the proposed Raw-to-HDR reconstruction model, as well as our newly captured dataset in the experiments.

Rongfeng Lu, Hangyu Chen, Zunjie Zhu et al.

Thermography is especially valuable for the military and other users of surveillance cameras. Some recent methods based on Neural Radiance Fields (NeRF) are proposed to reconstruct the thermal scenes in 3D from a set of thermal and RGB images. However, unlike NeRF, 3D Gaussian splatting (3DGS) prevails due to its rapid training and real-time rendering. In this work, we propose ThermalGaussian, the first thermal 3DGS approach capable of rendering high-quality images in RGB and thermal modalities. We first calibrate the RGB camera and the thermal camera to ensure that both modalities are accurately aligned. Subsequently, we use the registered images to learn the multimodal 3D Gaussians. To prevent the overfitting of any single modality, we introduce several multimodal regularization constraints. We also develop smoothing constraints tailored to the physical characteristics of the thermal modality. Besides, we contribute a real-world dataset named RGBT-Scenes, captured by a hand-hold thermal-infrared camera, facilitating future research on thermal scene reconstruction. We conduct comprehensive experiments to show that ThermalGaussian achieves photorealistic rendering of thermal images and improves the rendering quality of RGB images. With the proposed multimodal regularization constraints, we also reduced the model's storage cost by 90%. Our project page is at https://thermalgaussian.github.io/.

Pengju Wang, Bochao Liu, Dan Zeng et al.

In practical scenarios, federated learning frequently necessitates training personalized models for each client using heterogeneous data. This paper proposes a backbone self-distillation approach to facilitate personalized federated learning. In this approach, each client trains its local model and only sends the backbone weights to the server. These weights are then aggregated to create a global backbone, which is returned to each client for updating. However, the client's local backbone lacks personalization because of the common representation. To solve this problem, each client further performs backbone self-distillation by using the global backbone as a teacher and transferring knowledge to update the local backbone. This process involves learning two components: the shared backbone for common representation and the private head for local personalization, which enables effective global knowledge transfer. Extensive experiments and comparisons with 12 state-of-the-art approaches demonstrate the effectiveness of our approach.

Quan Chen, Tingyu Wang, Zihao Yang et al.

Cross-view geo-localization aims to match images of the same target from different platforms, e.g., drone and satellite. It is a challenging task due to the changing appearance of targets and environmental content from different views. Most methods focus on obtaining more comprehensive information through feature map segmentation, while inevitably destroying the image structure, and are sensitive to the shifting and scale of the target in the query. To address the above issues, we introduce simple yet effective part-based representation learning, shifting-dense partition learning (SDPL). We propose a dense partition strategy (DPS), dividing the image into multiple parts to explore contextual information while explicitly maintaining the global structure. To handle scenarios with non-centered targets, we further propose the shifting-fusion strategy, which generates multiple sets of parts in parallel based on various segmentation centers, and then adaptively fuses all features to integrate their anti-offset ability. Extensive experiments show that SDPL is robust to position shifting, and performs com-petitively on two prevailing benchmarks, University-1652 and SUES-200. In addition, SDPL shows satisfactory compatibility with a variety of backbone networks (e.g., ResNet and Swin). https://github.com/C-water/SDPL release.

Hansong Zhang, Shikun Li, Dan Zeng et al.

As the size of the datasets getting larger, accurately annotating such datasets is becoming more impractical due to the expensiveness on both time and economy. Therefore, crowd-sourcing has been widely adopted to alleviate the cost of collecting labels, which also inevitably introduces label noise and eventually degrades the performance of the model. To learn from crowd-sourcing annotations, modeling the expertise of each annotator is a common but challenging paradigm, because the annotations collected by crowd-sourcing are usually highly-sparse. To alleviate this problem, we propose Coupled Confusion Correction (CCC), where two models are simultaneously trained to correct the confusion matrices learned by each other. Via bi-level optimization, the confusion matrices learned by one model can be corrected by the distilled data from the other. Moreover, we cluster the ``annotator groups'' who share similar expertise so that their confusion matrices could be corrected together. In this way, the expertise of the annotators, especially of those who provide seldom labels, could be better captured. Remarkably, we point out that the annotation sparsity not only means the average number of labels is low, but also there are always some annotators who provide very few labels, which is neglected by previous works when constructing synthetic crowd-sourcing annotations. Based on that, we propose to use Beta distribution to control the generation of the crowd-sourcing labels so that the synthetic annotations could be more consistent with the real-world ones. Extensive experiments are conducted on two types of synthetic datasets and three real-world datasets, the results of which demonstrate that CCC significantly outperforms state-of-the-art approaches. Source codes are available at: https://github.com/Hansong-Zhang/CCC.

Yeqi He, Liang Li, Jiehua Zhang et al.

Training generative models with limited data presents severe challenges of mode collapse. A common approach is to adapt a large pretrained generative model upon a target domain with very few samples (fewer than 10), known as few-shot generative model adaptation. However, existing methods often suffer from forgetting source domain identity knowledge during adaptation, which degrades the quality of generated images in the target domain. To address this, we propose Identity Injection and Preservation (I$^2$P), which leverages identity injection and consistency alignment to preserve the source identity knowledge. Specifically, we first introduce an identity injection module that integrates source domain identity knowledge into the target domain's latent space, ensuring the generated images retain key identity knowledge of the source domain. Second, we design an identity substitution module, which includes a style-content decoupler and a reconstruction modulator, to further enhance source domain identity preservation. We enforce identity consistency constraints by aligning features from identity substitution, thereby preserving identity knowledge. Both quantitative and qualitative experiments show that our method achieves substantial improvements over state-of-the-art methods on multiple public datasets and 5 metrics.

Gaoxiang Cong, Yuankai Qi, Liang Li et al.

Given a script, the challenge in Movie Dubbing (Visual Voice Cloning, V2C) is to generate speech that aligns well with the video in both time and emotion, based on the tone of a reference audio track. Existing state-of-the-art V2C models break the phonemes in the script according to the divisions between video frames, which solves the temporal alignment problem but leads to incomplete phoneme pronunciation and poor identity stability. To address this problem, we propose StyleDubber, which switches dubbing learning from the frame level to phoneme level. It contains three main components: (1) A multimodal style adaptor operating at the phoneme level to learn pronunciation style from the reference audio, and generate intermediate representations informed by the facial emotion presented in the video; (2) An utterance-level style learning module, which guides both the mel-spectrogram decoding and the refining processes from the intermediate embeddings to improve the overall style expression; And (3) a phoneme-guided lip aligner to maintain lip sync. Extensive experiments on two of the primary benchmarks, V2C and Grid, demonstrate the favorable performance of the proposed method as compared to the current stateof-the-art. The code will be made available at https://github.com/GalaxyCong/StyleDubber.

Linwei Chen, Lin Gu, Liang Li et al.

While Dynamic Convolution (DY-Conv) has shown promising performance by enabling adaptive weight selection through multiple parallel weights combined with an attention mechanism, the frequency response of these weights tends to exhibit high similarity, resulting in high parameter costs but limited adaptability. In this work, we introduce Frequency Dynamic Convolution (FDConv), a novel approach that mitigates these limitations by learning a fixed parameter budget in the Fourier domain. FDConv divides this budget into frequency-based groups with disjoint Fourier indices, enabling the construction of frequency-diverse weights without increasing the parameter cost. To further enhance adaptability, we propose Kernel Spatial Modulation (KSM) and Frequency Band Modulation (FBM). KSM dynamically adjusts the frequency response of each filter at the spatial level, while FBM decomposes weights into distinct frequency bands in the frequency domain and modulates them dynamically based on local content. Extensive experiments on object detection, segmentation, and classification validate the effectiveness of FDConv. We demonstrate that when applied to ResNet-50, FDConv achieves superior performance with a modest increase of +3.6M parameters, outperforming previous methods that require substantial increases in parameter budgets (e.g., CondConv +90M, KW +76.5M). Moreover, FDConv seamlessly integrates into a variety of architectures, including ConvNeXt, Swin-Transformer, offering a flexible and efficient solution for modern vision tasks. The code is made publicly available at https://github.com/Linwei-Chen/FDConv.

Quan Chen, Xiaokai Yang, Tingyu Wang et al.

Salient object detection (SOD), a foundational task in computer vision, has advanced from single-modal to multi-modal paradigms to enhance generalization. However, most existing SOD methods assume low-noise visual conditions, overlooking the degradation of segmentation accuracy caused by weather-induced noise in real-world scenarios. In this paper, we propose a SOD framework tailored for diverse weather conditions, encompassing a specific encoder and a replaceable decoder. To enable handling of varying weather noises, we introduce a one-hot vector as a noise indicator to represent different weather types and design a Noise Indicator Fusion Module (NIFM). The NIFM takes both semantic features and the noise indicator as dual inputs and is inserted between consecutive stages of the encoder to embed weather-aware priors via adaptive feature modulation. Critically, the proposed specific encoder retains compatibility with mainstream SOD decoders. Extensive experiments are conducted on the WXSOD dataset under varying training data scales (100%, 50%, 30% of the full training set), three encoder and seven decoder configurations. Results show that the proposed SOD framework (particularly the NIFM-enhanced specific encoder) improves segmentation accuracy under complex weather conditions compared to a vanilla encoder.

Peihua Deng, Jiehua Zhang, Xichun Sheng et al.

This paper explores the Class-Incremental Source-Free Unsupervised Domain Adaptation (CI-SFUDA) problem, where the unlabeled target data come incrementally without access to labeled source instances. This problem poses two challenges, the interference of similar source-class knowledge in target-class representation learning and the shocks of new target knowledge to old ones. To address them, we propose the Multi-Granularity Class Prototype Topology Distillation (GROTO) algorithm, which effectively transfers the source knowledge to the class-incremental target domain. Concretely, we design the multi-granularity class prototype self-organization module and the prototype topology distillation module. First, we mine the positive classes by modeling accumulation distributions. Next, we introduce multi-granularity class prototypes to generate reliable pseudo-labels, and exploit them to promote the positive-class target feature self-organization. Second, the positive-class prototypes are leveraged to construct the topological structures of source and target feature spaces. Then, we perform the topology distillation to continually mitigate the shocks of new target knowledge to old ones. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on three public datasets. Code is available at https://github.com/dengpeihua/GROTO.

Zhiwen Yang, Jiehua Zhang, Liang Li et al.

Image-guided depth completion aims at generating a dense depth map from sparse LiDAR data and RGB image. Recent methods have shown promising performance by reformulating it as a classification problem with two sub-tasks: depth discretization and probability prediction. They divide the depth range into several discrete depth values as depth categories, serving as priors for scene depth distributions. However, previous depth discretization methods are easy to be impacted by depth distribution variations across different scenes, resulting in suboptimal scene depth distribution priors. To address the above problem, we propose a progressive depth decoupling and modulating network, which incrementally decouples the depth range into bins and adaptively generates multi-scale dense depth maps in multiple stages. Specifically, we first design a Bins Initializing Module (BIM) to construct the seed bins by exploring the depth distribution information within a sparse depth map, adapting variations of depth distribution. Then, we devise an incremental depth decoupling branch to progressively refine the depth distribution information from global to local. Meanwhile, an adaptive depth modulating branch is developed to progressively improve the probability representation from coarse-grained to fine-grained. And the bi-directional information interactions are proposed to strengthen the information interaction between those two branches (sub-tasks) for promoting information complementation in each branch. Further, we introduce a multi-scale supervision mechanism to learn the depth distribution information in latent features and enhance the adaptation capability across different scenes. Experimental results on public datasets demonstrate that our method outperforms the state-of-the-art methods. The code will be open-sourced at [this https URL](https://github.com/Cisse-away/PDDM).

Zhedong Zhang, Liang Li, Jiehua Zhang et al.

Existing symbolic music generation methods usually utilize discriminator to improve the quality of generated music via global perception of music. However, considering the complexity of information in music, such as rhythm and melody, a single discriminator cannot fully reflect the differences in these two primary dimensions of music. In this work, we propose to decouple the melody and rhythm from music, and design corresponding fine-grained discriminators to tackle the aforementioned issues. Specifically, equipped with a pitch augmentation strategy, the melody discriminator discerns the melody variations presented by the generated samples. By contrast, the rhythm discriminator, enhanced with bar-level relative positional encoding, focuses on the velocity of generated notes. Such a design allows the generator to be more explicitly aware of which aspects should be adjusted in the generated music, making it easier to mimic human-composed music. Experimental results on the POP909 benchmark demonstrate the favorable performance of the proposed method compared to several state-of-the-art methods in terms of both objective and subjective metrics.

Yeqi He, Liang Li, Zhiwen Yang et al.

Diffusion models have demonstrated remarkable performance in image generation, particularly within the domain of style transfer. Prevailing style transfer approaches typically leverage pre-trained diffusion models' robust feature extraction capabilities alongside external modular control pathways to explicitly impose style guidance signals. However, these methods often fail to capture complex style reference or retain the identity of user-provided content images, thus falling into the trap of style-content balance. Thus, we propose a training-free style transfer approach via $\textbf{h}$eterogeneous $\textbf{a}$ttention $\textbf{m}$odulation ($\textbf{HAM}$) to protect identity information during image/text-guided style reference transfer, thereby addressing the style-content trade-off challenge. Specifically, we first introduces style noise initialization to initialize latent noise for diffusion. Then, during the diffusion process, it innovatively employs HAM for different attention mechanisms, including Global Attention Regulation (GAR) and Local Attention Transplantation (LAT), which better preserving the details of the content image while capturing complex style references. Our approach is validated through a series of qualitative and quantitative experiments, achieving state-of-the-art performance on multiple quantitative metrics.

Boyang Guo, Liang Li, Lin Peng et al.

Prompt learning has emerged as an efficient alternative to fine-tuning pre-trained vision-language models (VLMs). Despite its promise, current methods still struggle to maintain tail-class discriminability when adapting to class-imbalanced datasets. In this work, we propose cluster-aware neural collapse prompt tuning (CPT), which enhances the discriminability of tail classes in prompt-tuned VLMs without sacrificing their overall generalization. First, we design a cluster-invariant space by mining semantic assignments from the pre-trained VLM and mapping them to prompt-tuned features. This computes cluster-level boundaries and restricts the constraints to local neighborhoods, which reduces interference with the global semantic structure of the pre-trained VLM. Second, we introduce neural-collapse-driven discriminability optimization with three losses: textual Equiangular Tight Frame (ETF) separation loss, class-wise convergence loss, and rotation stabilization loss. These losses work together to shape intra-cluster geometry for better inter-class separation and intra-class alignment. Extensive experiments on 11 diverse datasets demonstrate that CPT outperforms SOTA methods, with stronger performance on long-tail classes and good generalization to unseen classes.

Jiong Yin, Liang Li, Jiehua Zhang et al.

Audio-visual multi-task incremental learning aims to continuously learn from multiple audio-visual tasks without the need for joint training on all tasks. The challenge of the problem is how to preserve the old task knowledge while facilitating the learning of new task with previous experiences. To address these challenges, we introduce a three-stage Progressive Homeostatic and Plastic audio-visual prompt (PHP) method. In the shallow phase, we design the task-shared modality aggregating adapter to foster cross-task and cross-modal audio-visual representation learning to enhance shared understanding between tasks. In the middle phase, we propose the task-specific modality-shared dynamic generating adapter, which constructs prompts that are tailored to individual tasks while remaining general across modalities, which balances the models ability to retain knowledge against forgetting with its potential for versatile multi-task transferability. In the deep phase, we introduce the task-specific modality-independent prompts to further refine the understand ability by targeting individual information for each task and modality. By incorporating these three phases, PHP retains task-specific prompts while adapting shared parameters for new tasks to effectively balance knowledge sharing and specificity. Our method achieves SOTA performance in different orders of four tasks (AVE, AVVP, AVS and AVQA). Our code can be available at https://github.com/ENJOY-Yin-jiong/PHP.

Hang Xu, Xinyuan Liu, Haonan Xu et al.

Oriented object detection has been developed rapidly in the past few years, where rotation equivariance is crucial for detectors to predict rotated boxes. It is expected that the prediction can maintain the corresponding rotation when objects rotate, but severe mutation in angular prediction is sometimes observed when objects rotate near the boundary angle, which is well-known boundary discontinuity problem. The problem has been long believed to be caused by the sharp loss increase at the angular boundary, and widely used joint-optim IoU-like methods deal with this problem by loss-smoothing. However, we experimentally find that even state-of-the-art IoU-like methods actually fail to solve the problem. On further analysis, we find that the key to solution lies in encoding mode of the smoothing function rather than in joint or independent optimization. In existing IoU-like methods, the model essentially attempts to fit the angular relationship between box and object, where the break point at angular boundary makes the predictions highly unstable.To deal with this issue, we propose a dual-optimization paradigm for angles. We decouple reversibility and joint-optim from single smoothing function into two distinct entities, which for the first time achieves the objectives of both correcting angular boundary and blending angle with other parameters.Extensive experiments on multiple datasets show that boundary discontinuity problem is well-addressed. Moreover, typical IoU-like methods are improved to the same level without obvious performance gap. The code is available at https://github.com/hangxu-cv/cvpr24acm.

Jinshuo Liu, Bingtao Ma, Junlin Su et al.

Category-level object pose estimation is fundamental for embodied intelligence, yet achieving robust generalization to unseen instances remains challenging. However, existing methods mainly rely on simple feature extraction and aggregation, which struggle to capture category-shared topological structures and conduct semantic keypoint modeling, limiting their generalization. To address these, we propose a \textbf{T}opology-Aware Learning with \textbf{S}emantic \textbf{M}amba for Category-Level \textbf{P}ose Estimation framework (TSM-Pose). Specifically, we introduce a Topology Extractor to capture the global topological representation of the point cloud, which is integrated into local geometry features and enables robust category-level structural representation. Simultaneously, we propose a Mamba-based Global Semantic Aggregator that injects semantics priors into keypoints to enhance their expressiveness and leverages multiple TwinMamba blocks to model long-range dependencies for more effective global feature aggregation. Extensive experiments on three benchmark datasets (REAL275, CAMERA25, and HouseCat6D) demonstrate that TSM-Pose outperforms existing state-of-the-art methods.

Liuxin Bao, Xiaofei Zhou, Xiankai Lu et al.

Depth images and thermal images contain the spatial geometry information and surface temperature information, which can act as complementary information for the RGB modality. However, the quality of the depth and thermal images is often unreliable in some challenging scenarios, which will result in the performance degradation of the two-modal based salient object detection (SOD). Meanwhile, some researchers pay attention to the triple-modal SOD task, where they attempt to explore the complementarity of the RGB image, the depth image, and the thermal image. However, existing triple-modal SOD methods fail to perceive the quality of depth maps and thermal images, which leads to performance degradation when dealing with scenes with low-quality depth and thermal images. Therefore, we propose a quality-aware selective fusion network (QSF-Net) to conduct VDT salient object detection, which contains three subnets including the initial feature extraction subnet, the quality-aware region selection subnet, and the region-guided selective fusion subnet. Firstly, except for extracting features, the initial feature extraction subnet can generate a preliminary prediction map from each modality via a shrinkage pyramid architecture. Then, we design the weakly-supervised quality-aware region selection subnet to generate the quality-aware maps. Concretely, we first find the high-quality and low-quality regions by using the preliminary predictions, which further constitute the pseudo label that can be used to train this subnet. Finally, the region-guided selective fusion subnet purifies the initial features under the guidance of the quality-aware maps, and then fuses the triple-modal features and refines the edge details of prediction maps through the intra-modality and inter-modality attention (IIA) module and the edge refinement (ER) module, respectively. Extensive experiments are performed on VDT-2048

Boyuan Peng, Jiaju Chen, P. Bilha Githinji et al.

Cell segmentation is essential in biomedical research for analyzing cellular morphology and behavior. Deep learning methods, particularly convolutional neural networks (CNNs), have revolutionized cell segmentation by extracting intricate features from images. However, the robustness of these methods under microscope optical aberrations remains a critical challenge. This study evaluates cell image segmentation models under optical aberrations from fluorescence and bright field microscopy. By simulating different types of aberrations, including astigmatism, coma, spherical aberration, trefoil, and mixed aberrations, we conduct a thorough evaluation of various cell instance segmentation models using the DynamicNuclearNet (DNN) and LIVECell datasets, representing fluorescence and bright field microscopy cell datasets, respectively. We train and test several segmentation models, including the Otsu threshold method and Mask R-CNN with different network heads (FPN, C3) and backbones (ResNet, VGG, Swin Transformer), under aberrated conditions. Additionally, we provide usage recommendations for the Cellpose 2.0 Toolbox on complex cell degradation images. The results indicate that the combination of FPN and SwinS demonstrates superior robustness in handling simple cell images affected by minor aberrations. In contrast, Cellpose 2.0 proves effective for complex cell images under similar conditions. Furthermore, we innovatively propose the Point Spread Function Image Label Classification Model (PLCM). This model can quickly and accurately identify aberration types and amplitudes from PSF images, assisting researchers without optical training. Through PLCM, researchers can better apply our proposed cell segmentation guidelines.

Jinkai Zheng, Xinchen Liu, Boyue Zhang et al.

Existing studies for gait recognition primarily utilized sequences of either binary silhouette or human parsing to encode the shapes and dynamics of persons during walking. Silhouettes exhibit accurate segmentation quality and robustness to environmental variations, but their low information entropy may result in sub-optimal performance. In contrast, human parsing provides fine-grained part segmentation with higher information entropy, but the segmentation quality may deteriorate due to the complex environments. To discover the advantages of silhouette and parsing and overcome their limitations, this paper proposes a novel cross-granularity alignment gait recognition method, named XGait, to unleash the power of gait representations of different granularity. To achieve this goal, the XGait first contains two branches of backbone encoders to map the silhouette sequences and the parsing sequences into two latent spaces, respectively. Moreover, to explore the complementary knowledge across the features of two representations, we design the Global Cross-granularity Module (GCM) and the Part Cross-granularity Module (PCM) after the two encoders. In particular, the GCM aims to enhance the quality of parsing features by leveraging global features from silhouettes, while the PCM aligns the dynamics of human parts between silhouette and parsing features using the high information entropy in parsing sequences. In addition, to effectively guide the alignment of two representations with different granularity at the part level, an elaborate-designed learnable division mechanism is proposed for the parsing features. Comprehensive experiments on two large-scale gait datasets not only show the superior performance of XGait with the Rank-1 accuracy of 80.5% on Gait3D and 88.3% CCPG but also reflect the robustness of the learned features even under challenging conditions like occlusions and cloth changes.

Zhedong Zhang, Liang Li, Chenggang Yan et al.

Movie dubbing describes the process of transforming a script into speech that aligns temporally and emotionally with a given movie clip while exemplifying the speaker's voice demonstrated in a short reference audio clip. This task demands the model bridge character performances and complicated prosody structures to build a high-quality video-synchronized dubbing track. The limited scale of movie dubbing datasets, along with the background noise inherent in audio data, hinder the acoustic modeling performance of trained models. To address these issues, we propose an acoustic-prosody disentangled two-stage method to achieve high-quality dubbing generation with precise prosody alignment. First, we propose a prosody-enhanced acoustic pre-training to develop robust acoustic modeling capabilities. Then, we freeze the pre-trained acoustic system and design a disentangled framework to model prosodic text features and dubbing style while maintaining acoustic quality. Additionally, we incorporate an in-domain emotion analysis module to reduce the impact of visual domain shifts across different movies, thereby enhancing emotion-prosody alignment. Extensive experiments show that our method performs favorably against the state-of-the-art models on two primary benchmarks. The demos are available at https://zzdoog.github.io/ProDubber/.

Lifeng Lin, Rongfeng Lu, Quan Chen et al.

Sparse-view 3D reconstruction is a fundamental yet challenging task in practical 3D reconstruction applications. Recently, many methods based on the 3D Gaussian Splatting (3DGS) framework have been proposed to address sparse-view 3D reconstruction. Although these methods have made considerable advancements, they still show significant issues with overfitting. To reduce the overfitting, we introduce VGNC, a novel Validation-guided Gaussian Number Control (VGNC) approach based on generative novel view synthesis (NVS) models. To the best of our knowledge, this is the first attempt to alleviate the overfitting issue of sparse-view 3DGS with generative validation images. Specifically, we first introduce a validation image generation method based on a generative NVS model. We then propose a Gaussian number control strategy that utilizes generated validation images to determine the optimal Gaussian numbers, thereby reducing the issue of overfitting. We conducted detailed experiments on various sparse-view 3DGS baselines and datasets to evaluate the effectiveness of VGNC. Extensive experiments show that our approach not only reduces overfitting but also improves rendering quality on the test set while decreasing the number of Gaussian points. This reduction lowers storage demands and accelerates both training and rendering. The code will be released.

Huizai Yao, Sicheng Zhao, Shuo Lu et al.

Source-Free Object Detection (SFOD) enables knowledge transfer from a source domain to an unsupervised target domain for object detection without access to source data. Most existing SFOD approaches are either confined to conventional object detection (OD) models like Faster R-CNN or designed as general solutions without tailored adaptations for novel OD architectures, especially Detection Transformer (DETR). In this paper, we introduce Feature Reweighting ANd Contrastive Learning NetworK (FRANCK), a novel SFOD framework specifically designed to perform query-centric feature enhancement for DETRs. FRANCK comprises four key components: (1) an Objectness Score-based Sample Reweighting (OSSR) module that computes attention-based objectness scores on multi-scale encoder feature maps, reweighting the detection loss to emphasize less-recognized regions; (2) a Contrastive Learning with Matching-based Memory Bank (CMMB) module that integrates multi-level features into memory banks, enhancing class-wise contrastive learning; (3) an Uncertainty-weighted Query-fused Feature Distillation (UQFD) module that improves feature distillation through prediction quality reweighting and query feature fusion; and (4) an improved self-training pipeline with a Dynamic Teacher Updating Interval (DTUI) that optimizes pseudo-label quality. By leveraging these components, FRANCK effectively adapts a source-pre-trained DETR model to a target domain with enhanced robustness and generalization. Extensive experiments on several widely used benchmarks demonstrate that our method achieves state-of-the-art performance, highlighting its effectiveness and compatibility with DETR-based SFOD models.

Longjian Zeng, Zunjie Zhu, Rongfeng Lu et al.

In recent years, foundation models for monocular depth estimation have received increasing attention. Current methods mainly address typical daylight conditions, but their effectiveness notably decreases in low-light environments. There is a lack of robust foundational models for monocular depth estimation specifically designed for low-light scenarios. This largely stems from the absence of large-scale, high-quality paired depth datasets for low-light conditions and the effective parameter-efficient fine-tuning (PEFT) strategy. To address these challenges, we propose DepthDark, a robust foundation model for low-light monocular depth estimation. We first introduce a flare-simulation module and a noise-simulation module to accurately simulate the imaging process under nighttime conditions, producing high-quality paired depth datasets for low-light conditions. Additionally, we present an effective low-light PEFT strategy that utilizes illumination guidance and multiscale feature fusion to enhance the model's capability in low-light environments. Our method achieves state-of-the-art depth estimation performance on the challenging nuScenes-Night and RobotCar-Night datasets, validating its effectiveness using limited training data and computing resources.

Shaoxiong Zhang, Jinkai Zheng, Shangdong Zhu et al.

Gait recognition aims to identify individuals based on their body shape and walking patterns. Though much progress has been achieved driven by deep learning, gait recognition in real-world surveillance scenarios remains quite challenging to current methods. Conventional approaches, which rely on periodic gait cycles and controlled environments, struggle with the non-periodic and occluded silhouette sequences encountered in the wild. In this paper, we propose a novel framework, TrackletGait, designed to address these challenges in the wild. We propose Random Tracklet Sampling, a generalization of existing sampling methods, which strikes a balance between robustness and representation in capturing diverse walking patterns. Next, we introduce Haar Wavelet-based Downsampling to preserve information during spatial downsampling. Finally, we present a Hardness Exclusion Triplet Loss, designed to exclude low-quality silhouettes by discarding hard triplet samples. TrackletGait achieves state-of-the-art results, with 77.8 and 80.4 rank-1 accuracy on the Gait3D and GREW datasets, respectively, while using only 10.3M backbone parameters. Extensive experiments are also conducted to further investigate the factors affecting gait recognition in the wild.

Haofan Ren, Zunjie Zhu, Xiang Chen et al.

Neural fields are now the central focus of research in 3D vision and computer graphics. Existing methods mainly focus on various scene representations, such as neural points and 3D Gaussians. However, few works have studied the rendering process to enhance the neural fields. In this work, we propose a plug-in method named K-Buffers that leverages multiple buffers to improve the rendering performance. Our method first renders K buffers from scene representations and constructs K pixel-wise feature maps. Then, We introduce a K-Feature Fusion Network (KFN) to merge the K pixel-wise feature maps. Finally, we adopt a feature decoder to generate the rendering image. We also introduce an acceleration strategy to improve rendering speed and quality. We apply our method to well-known radiance field baselines, including neural point fields and 3D Gaussian Splatting (3DGS). Extensive experiments demonstrate that our method effectively enhances the rendering performance of neural point fields and 3DGS.

Zunjie Zhu, Yan Zhao, Yihan Hu et al.

The motion capture system that supports full-body virtual representation is of key significance for virtual reality. Compared to vision-based systems, full-body pose estimation from sparse tracking signals is not limited by environmental conditions or recording range. However, previous works either face the challenge of wearing additional sensors on the pelvis and lower-body or rely on external visual sensors to obtain global positions of key joints. To improve the practicality of the technology for virtual reality applications, we estimate full-body poses using only inertial data obtained from three Inertial Measurement Unit (IMU) sensors worn on the head and wrists, thereby reducing the complexity of the hardware system. In this work, we propose a method called Progressive Inertial Poser (ProgIP) for human pose estimation, which combines neural network estimation with a human dynamics model, considers the hierarchical structure of the kinematic chain, and employs a multi-stage progressive network estimation with increased depth to reconstruct full-body motion in real time. The encoder combines Transformer Encoder and bidirectional LSTM (TE-biLSTM) to flexibly capture the temporal dependencies of the inertial sequence, while the decoder based on multi-layer perceptrons (MLPs) transforms high-dimensional features and accurately projects them onto Skinned Multi-Person Linear (SMPL) model parameters. Quantitative and qualitative experimental results on multiple public datasets show that our method outperforms state-of-the-art methods with the same inputs, and is comparable to recent works using six IMU sensors.

Ying Fu, Yu Li, Shaodi You et al.

The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, and medium properties from images. In recent years, deep learning has shown promising improvements for various vision tasks, and when combined with physics-based vision, these approaches can enhance the robustness and accuracy of vision systems. This technical report summarizes the outcomes of the Physics-Based Vision Meets Deep Learning (PBDL) 2024 challenge, held in CVPR 2024 workshop. The challenge consisted of eight tracks, focusing on Low-Light Enhancement and Detection as well as High Dynamic Range (HDR) Imaging. This report details the objectives, methodologies, and results of each track, highlighting the top-performing solutions and their innovative approaches.

P. Bilha Githinji, Xi Yuan, Zhenglin Chen et al.

Realizing sufficient separability between the distributions of healthy and pathological samples is a critical obstacle for pathology detection convolutional models. Moreover, these models exhibit a bias for contrast-based images, with diminished performance on texture-based medical images. This study introduces the notion of a population-level context for pathology detection and employs a graph theoretic approach to model and incorporate it into the latent code of an autoencoder via a refinement module we term PopuSense. PopuSense seeks to capture additional intra-group variations inherent in biomedical data that a local or global context of the convolutional model might miss or smooth out. Proof-of-concept experiments on contrast-based and texture-based images, with minimal adaptation, encounter the existing preference for intensity-based input. Nevertheless, PopuSense demonstrates improved separability in contrast-based images, presenting an additional avenue for refining representations learned by a model.

Yunbin Tu, Liang Li, Chenggang Yan et al.

Change captioning is to use a natural language sentence to describe the fine-grained disagreement between two similar images. Viewpoint change is the most typical distractor in this task, because it changes the scale and location of the objects and overwhelms the representation of real change. In this paper, we propose a Relation-embedded Representation Reconstruction Network (R$^3$Net) to explicitly distinguish the real change from the large amount of clutter and irrelevant changes. Specifically, a relation-embedded module is first devised to explore potential changed objects in the large amount of clutter. Then, based on the semantic similarities of corresponding locations in the two images, a representation reconstruction module (RRM) is designed to learn the reconstruction representation and further model the difference representation. Besides, we introduce a syntactic skeleton predictor (SSP) to enhance the semantic interaction between change localization and caption generation. Extensive experiments show that the proposed method achieves the state-of-the-art results on two public datasets.

Qiang Zhao, Bin Chen, Hang Xu et al.

As one of the most fundamental and challenging problems in computer vision, object detection tries to locate object instances and find their categories in natural images. The most important step in the evaluation of object detection algorithm is calculating the intersection-over-union (IoU) between the predicted bounding box and the ground truth one. Although this procedure is well-defined and solved for planar images, it is not easy for spherical image object detection. Existing methods either compute the IoUs based on biased bounding box representations or make excessive approximations, thus would give incorrect results. In this paper, we first identify that spherical rectangles are unbiased bounding boxes for objects in spherical images, and then propose an analytical method for IoU calculation without any approximations. Based on the unbiased representation and calculation, we also present an anchor free object detection algorithm for spherical images. The experiments on two spherical object detection datasets show that the proposed method can achieve better performance than existing methods.

Jinkai Zheng, Xinchen Liu, Chenggang Yan et al.

Gait, i.e., the movement pattern of human limbs during locomotion, is a promising biometric for the identification of persons. Despite significant improvement in gait recognition with deep learning, existing studies still neglect a more practical but challenging scenario -- unsupervised cross-domain gait recognition which aims to learn a model on a labeled dataset then adapts it to an unlabeled dataset. Due to the domain shift and class gap, directly applying a model trained on one source dataset to other target datasets usually obtains very poor results. Therefore, this paper proposes a Transferable Neighborhood Discovery (TraND) framework to bridge the domain gap for unsupervised cross-domain gait recognition. To learn effective prior knowledge for gait representation, we first adopt a backbone network pre-trained on the labeled source data in a supervised manner. Then we design an end-to-end trainable approach to automatically discover the confident neighborhoods of unlabeled samples in the latent space. During training, the class consistency indicator is adopted to select confident neighborhoods of samples based on their entropy measurements. Moreover, we explore a high-entropy-first neighbor selection strategy, which can effectively transfer prior knowledge to the target domain. Our method achieves state-of-the-art results on two public datasets, i.e., CASIA-B and OU-LP.

Xin He, Shihao Wang, Xiaowen Chu et al.

The COVID-19 pandemic has spread globally for several months. Because its transmissibility and high pathogenicity seriously threaten people's lives, it is crucial to accurately and quickly detect COVID-19 infection. Many recent studies have shown that deep learning (DL) based solutions can help detect COVID-19 based on chest CT scans. However, most existing work focuses on 2D datasets, which may result in low quality models as the real CT scans are 3D images. Besides, the reported results span a broad spectrum on different datasets with a relatively unfair comparison. In this paper, we first use three state-of-the-art 3D models (ResNet3D101, DenseNet3D121, and MC3\_18) to establish the baseline performance on the three publicly available chest CT scan datasets. Then we propose a differentiable neural architecture search (DNAS) framework to automatically search for the 3D DL models for 3D chest CT scans classification with the Gumbel Softmax technique to improve the searching efficiency. We further exploit the Class Activation Mapping (CAM) technique on our models to provide the interpretability of the results. The experimental results show that our automatically searched models (CovidNet3D) outperform the baseline human-designed models on the three datasets with tens of times smaller model size and higher accuracy. Furthermore, the results also verify that CAM can be well applied in CovidNet3D for COVID-19 datasets to provide interpretability for medical diagnosis.

Tingyu Wang, Zhedong Zheng, Chenggang Yan et al.

Cross-view geo-localization is to spot images of the same geographic target from different platforms, e.g., drone-view cameras and satellites. It is challenging in the large visual appearance changes caused by extreme viewpoint variations. Existing methods usually concentrate on mining the fine-grained feature of the geographic target in the image center, but underestimate the contextual information in neighbor areas. In this work, we argue that neighbor areas can be leveraged as auxiliary information, enriching discriminative clues for geolocalization. Specifically, we introduce a simple and effective deep neural network, called Local Pattern Network (LPN), to take advantage of contextual information in an end-to-end manner. Without using extra part estimators, LPN adopts a square-ring feature partition strategy, which provides the attention according to the distance to the image center. It eases the part matching and enables the part-wise representation learning. Owing to the square-ring partition design, the proposed LPN has good scalability to rotation variations and achieves competitive results on three prevailing benchmarks, i.e., University-1652, CVUSA and CVACT. Besides, we also show the proposed LPN can be easily embedded into other frameworks to further boost performance.

Chenggang Yan, Zhisheng Li, Yongbing Zhang et al.

The depth images denoising are increasingly becoming the hot research topic nowadays because they reflect the three-dimensional (3D) scene and can be applied in various fields of computer vision. But the depth images obtained from depth camera usually contain stains such as noise, which greatly impairs the performance of depth related applications. In this paper, considering that group-based image restoration methods are more effective in gathering the similarity among patches, a group based nuclear norm and learning graph (GNNLG) model was proposed. For each patch, we find and group the most similar patches within a searching window. The intrinsic low-rank property of the grouped patches is exploited in our model. In addition, we studied the manifold learning method and devised an effective optimized learning strategy to obtain the graph Laplacian matrix, which reflects the topological structure of image, to further impose the smoothing priors to the denoised depth image. To achieve fast speed and high convergence, the alternating direction method of multipliers (ADMM) is proposed to solve our GNNLG. The experimental results show that the proposed method is superior to other current state-of-the-art denoising methods in both subjective and objective criterion.

Yutian Lin, Lingxi Xie, Yu Wu et al.

Person re-identification (re-ID) is an important topic in computer vision. This paper studies the unsupervised setting of re-ID, which does not require any labeled information and thus is freely deployed to new scenarios. There are very few studies under this setting, and one of the best approach till now used iterative clustering and classification, so that unlabeled images are clustered into pseudo classes for a classifier to get trained, and the updated features are used for clustering and so on. This approach suffers two problems, namely, the difficulty of determining the number of clusters, and the hard quantization loss in clustering. In this paper, we follow the iterative training mechanism but discard clustering, since it incurs loss from hard quantization, yet its only product, image-level similarity, can be easily replaced by pairwise computation and a softened classification task. With these improvements, our approach becomes more elegant and is more robust to hyper-parameter changes. Experiments on two image-based and video-based datasets demonstrate state-of-the-art performance under the unsupervised re-ID setting.

Chenggang Yan, Biao Gong, Yuxuan Wei et al.

Hashing is an efficient method for nearest neighbor search in large-scale data space by embedding high-dimensional feature descriptors into a similarity preserving Hamming space with a low dimension. However, large-scale high-speed retrieval through binary code has a certain degree of reduction in retrieval accuracy compared to traditional retrieval methods. We have noticed that multi-view methods can well preserve the diverse characteristics of data. Therefore, we try to introduce the multi-view deep neural network into the hash learning field, and design an efficient and innovative retrieval model, which has achieved a significant improvement in retrieval performance. In this paper, we propose a supervised multi-view hash model which can enhance the multi-view information through neural networks. This is a completely new hash learning method that combines multi-view and deep learning methods. The proposed method utilizes an effective view stability evaluation method to actively explore the relationship among views, which will affect the optimization direction of the entire network. We have also designed a variety of multi-data fusion methods in the Hamming space to preserve the advantages of both convolution and multi-view. In order to avoid excessive computing resources on the enhancement procedure during retrieval, we set up a separate structure called memory network which participates in training together. The proposed method is systematically evaluated on the CIFAR-10, NUS-WIDE and MS-COCO datasets, and the results show that our method significantly outperforms the state-of-the-art single-view and multi-view hashing methods.