Haojie Li

Jian Shi, Baoli Sun, Xinchen Ye et al.

Segmenting dental plaque from images of medical reagent staining provides valuable information for diagnosis and the determination of follow-up treatment plan. However, accurate dental plaque segmentation is a challenging task that requires identifying teeth and dental plaque subjected to semantic-blur regions (i.e., confused boundaries in border regions between teeth and dental plaque) and complex variations of instance shapes, which are not fully addressed by existing methods. Therefore, we propose a semantic decomposition network (SDNet) that introduces two single-task branches to separately address the segmentation of teeth and dental plaque and designs additional constraints to learn category-specific features for each branch, thus facilitating the semantic decomposition and improving the performance of dental plaque segmentation. Specifically, SDNet learns two separate segmentation branches for teeth and dental plaque in a divide-and-conquer manner to decouple the entangled relation between them. Each branch that specifies a category tends to yield accurate segmentation. To help these two branches better focus on category-specific features, two constraint modules are further proposed: 1) contrastive constraint module (CCM) to learn discriminative feature representations by maximizing the distance between different category representations, so as to reduce the negative impact of semantic-blur regions on feature extraction; 2) structural constraint module (SCM) to provide complete structural information for dental plaque of various shapes by the supervision of an boundary-aware geometric constraint. Besides, we construct a large-scale open-source Stained Dental Plaque Segmentation dataset (SDPSeg), which provides high-quality annotations for teeth and dental plaque. Experimental results on SDPSeg datasets show SDNet achieves state-of-the-art performance.

Shijie Wang, Jianlong Chang, Zhihui Wang et al.

Fine-grained object retrieval aims to learn discriminative representation to retrieve visually similar objects. However, existing top-performing works usually impose pairwise similarities on the semantic embedding spaces or design a localization sub-network to continually fine-tune the entire model in limited data scenarios, thus resulting in convergence to suboptimal solutions. In this paper, we develop Fine-grained Retrieval Prompt Tuning (FRPT), which steers a frozen pre-trained model to perform the fine-grained retrieval task from the perspectives of sample prompting and feature adaptation. Specifically, FRPT only needs to learn fewer parameters in the prompt and adaptation instead of fine-tuning the entire model, thus solving the issue of convergence to suboptimal solutions caused by fine-tuning the entire model. Technically, a discriminative perturbation prompt (DPP) is introduced and deemed as a sample prompting process, which amplifies and even exaggerates some discriminative elements contributing to category prediction via a content-aware inhomogeneous sampling operation. In this way, DPP can make the fine-grained retrieval task aided by the perturbation prompts close to the solved task during the original pre-training. Thereby, it preserves the generalization and discrimination of representation extracted from input samples. Besides, a category-specific awareness head is proposed and regarded as feature adaptation, which removes the species discrepancies in features extracted by the pre-trained model using category-guided instance normalization. And thus, it makes the optimized features only include the discrepancies among subcategories. Extensive experiments demonstrate that our FRPT with fewer learnable parameters achieves the state-of-the-art performance on three widely-used fine-grained datasets.

Xinzhu Ma, Yongtao Wang, Yinmin Zhang et al.

In this work, we build a modular-designed codebase, formulate strong training recipes, design an error diagnosis toolbox, and discuss current methods for image-based 3D object detection. In particular, different from other highly mature tasks, e.g., 2D object detection, the community of image-based 3D object detection is still evolving, where methods often adopt different training recipes and tricks resulting in unfair evaluations and comparisons. What is worse, these tricks may overwhelm their proposed designs in performance, even leading to wrong conclusions. To address this issue, we build a module-designed codebase and formulate unified training standards for the community. Furthermore, we also design an error diagnosis toolbox to measure the detailed characterization of detection models. Using these tools, we analyze current methods in-depth under varying settings and provide discussions for some open questions, e.g., discrepancies in conclusions on KITTI-3D and nuScenes datasets, which have led to different dominant methods for these datasets. We hope that this work will facilitate future research in image-based 3D object detection. Our codes will be released at \url{https://github.com/OpenGVLab/3dodi}

Zengyuan Guo, Yuechen Yu, Pengyuan Lv et al.

Table structure recognition is a crucial part of document image analysis domain. Its difficulty lies in the need to parse the physical coordinates and logical indices of each cell at the same time. However, the existing methods are difficult to achieve both these goals, especially when the table splitting lines are blurred or tilted. In this paper, we propose an accurate and end-to-end transformer-based table structure recognition method, referred to as TRUST. Transformers are suitable for table structure recognition because of their global computations, perfect memory, and parallel computation. By introducing novel Transformer-based Query-based Splitting Module and Vertex-based Merging Module, the table structure recognition problem is decoupled into two joint optimization sub-tasks: multi-oriented table row/column splitting and table grid merging. The Query-based Splitting Module learns strong context information from long dependencies via Transformer networks, accurately predicts the multi-oriented table row/column separators, and obtains the basic grids of the table accordingly. The Vertex-based Merging Module is capable of aggregating local contextual information between adjacent basic grids, providing the ability to merge basic girds that belong to the same spanning cell accurately. We conduct experiments on several popular benchmarks including PubTabNet and SynthTable, our method achieves new state-of-the-art results. In particular, TRUST runs at 10 FPS on PubTabNet, surpassing the previous methods by a large margin.

Zhihao Xu, Shengjie Gong, Jiapeng Tang et al.

We present a novel approach for synthesizing 3D facial motions from audio sequences using key motion embeddings. Despite recent advancements in data-driven techniques, accurately mapping between audio signals and 3D facial meshes remains challenging. Direct regression of the entire sequence often leads to over-smoothed results due to the ill-posed nature of the problem. To this end, we propose a progressive learning mechanism that generates 3D facial animations by introducing key motion capture to decrease cross-modal mapping uncertainty and learning complexity. Concretely, our method integrates linguistic and data-driven priors through two modules: the linguistic-based key motion acquisition and the cross-modal motion completion. The former identifies key motions and learns the associated 3D facial expressions, ensuring accurate lip-speech synchronization. The latter extends key motions into a full sequence of 3D talking faces guided by audio features, improving temporal coherence and audio-visual consistency. Extensive experimental comparisons against existing state-of-the-art methods demonstrate the superiority of our approach in generating more vivid and consistent talking face animations. Consistent enhancements in results through the integration of our proposed learning scheme with existing methods underscore the efficacy of our approach. Our code and weights will be at the project website: \url{https://github.com/ffxzh/KMTalk}.

Haojie Li, Junwei Du, Guanfeng Liu et al.

Disentanglement techniques used in collaborative filtering uncover interaction intents between nodes, improving the interpretability of node representations and enhancing recommendation performance. However, existing disentanglement methods still face two problems. First, they focus on local structural features derived from direct node interactions and overlook the comprehensive graph structure, which limits disentanglement accuracy. Second, the disentanglement process depends on backpropagation signals derived from recommendation tasks and lacks direct supervision, which may lead to biases and overfitting. To address these issues, we propose the Intent Propagation Contrastive Collaborative Filtering (IPCCF) algorithm. Specifically, we design a double helix message propagation framework to more effectively extract the deep semantic information of nodes, thereby improving the model's understanding of interactions between nodes. We also develop an intent message propagation method that incorporates graph structure information into the disentanglement process, thereby expanding the consideration scope of disentanglement. In addition, contrastive learning techniques are employed to align node representations derived from structure and intents, providing direct supervision for the disentanglement process, mitigating biases, and enhancing the model's robustness to overfitting. Experiments on three real data graphs illustrate the superiority of the proposed approach.

Lupiao Hu, Fasheng Wang, Fangmei Chen et al.

Existing RGB-T salient object detection methods predominantly rely on manually aligned and annotated datasets, struggling to handle real-world scenarios with raw, unaligned RGB-T image pairs. In practical applications, due to significant cross-modal disparities such as spatial misalignment, scale variations, and viewpoint shifts, the performance of current methods drastically deteriorates on unaligned datasets. To address this issue, we propose an efficient RGB-T SOD method for real-world unaligned image pairs, termed Thin-Plate Spline-driven Semantic Correlation Learning Network (TPS-SCL). We employ a dual-stream MobileViT as the encoder, combined with efficient Mamba scanning mechanisms, to effectively model correlations between the two modalities while maintaining low parameter counts and computational overhead. To suppress interference from redundant background information during alignment, we design a Semantic Correlation Constraint Module (SCCM) to hierarchically constrain salient features. Furthermore, we introduce a Thin-Plate Spline Alignment Module (TPSAM) to mitigate spatial discrepancies between modalities. Additionally, a Cross-Modal Correlation Module (CMCM) is incorporated to fully explore and integrate inter-modal dependencies, enhancing detection performance. Extensive experiments on various datasets demonstrate that TPS-SCL attains state-of-the-art (SOTA) performance among existing lightweight SOD methods and outperforms mainstream RGB-T SOD approaches.

Xinwei Wu, Haojie Li, Hongyu Liu et al.

In this work, we study a critical research problem regarding the trustworthiness of large language models (LLMs): how LLMs behave when encountering ambiguous narrative text, with a particular focus on Chinese textual ambiguity. We created a benchmark dataset by collecting and generating ambiguous sentences with context and their corresponding disambiguated pairs, representing multiple possible interpretations. These annotated examples are systematically categorized into 3 main categories and 9 subcategories. Through experiments, we discovered significant fragility in LLMs when handling ambiguity, revealing behavior that differs substantially from humans. Specifically, LLMs cannot reliably distinguish ambiguous text from unambiguous text, show overconfidence in interpreting ambiguous text as having a single meaning rather than multiple meanings, and exhibit overthinking when attempting to understand the various possible meanings. Our findings highlight a fundamental limitation in current LLMs that has significant implications for their deployment in real-world applications where linguistic ambiguity is common, calling for improved approaches to handle uncertainty in language understanding. The dataset and code are publicly available at this GitHub repository: https://github.com/ictup/LLM-Chinese-Textual-Disambiguation.

Yongtang Bao, Chengjie Tang, Yuze Wang et al.

Reconstructing and segmenting scenes from unconstrained photo collections obtained from the Internet is a novel but challenging task. Unconstrained photo collections are easier to get than well-captured photo collections. These unconstrained images suffer from inconsistent lighting and transient occlusions, which makes segmentation challenging. Previous segmentation methods cannot address transient occlusions or accurately restore the scene's lighting conditions. Therefore, we propose Seg-Wild, an interactive segmentation method based on 3D Gaussian Splatting for unconstrained image collections, suitable for in-the-wild scenes. We integrate multi-dimensional feature embeddings for each 3D Gaussian and calculate the feature similarity between the feature embeddings and the segmentation target to achieve interactive segmentation in the 3D scene. Additionally, we introduce the Spiky 3D Gaussian Cutter (SGC) to smooth abnormal 3D Gaussians. We project the 3D Gaussians onto a 2D plane and calculate the ratio of 3D Gaussians that need to be cut using the SAM mask. We also designed a benchmark to evaluate segmentation quality in in-the-wild scenes. Experimental results demonstrate that compared to previous methods, Seg-Wild achieves better segmentation results and reconstruction quality. Our code will be available at https://github.com/Sugar0725/Seg-Wild.

Haojie Li, Mengjiao Zhang, Guanfeng Liu et al.

Graph self-supervised learning can reduce the need for labeled graph data and has been widely used in recommendation, social networks, and other web applications. However, existing methods often underuse high-frequency signals and may overfit to specific local patterns, which limits representation quality and generalization. We propose Frequency-Corrupt Based Graph Self-Supervised Learning (FC-GSSL), a method that builds corrupted graphs biased toward high-frequency information by corrupting nodes and edges according to their low-frequency contributions. These corrupted graphs are used as inputs to an autoencoder, while low-frequency and general features are reconstructed as supervision targets, forcing the model to fuse information from multiple frequency bands. We further design multiple sampling strategies and generate diverse corrupted graphs from the intersections and unions of the sampling results. By aligning node representations from these views, the model can discover useful frequency combinations, reduce reliance on specific high-frequency components, and improve robustness. Experiments on 14 datasets across node classification, graph prediction, and transfer learning show that FC-GSSL consistently improves performance and generalization.

Shenglun Chen, Xinzhu Ma, Hong Zhang et al.

Depth completion is a pivotal challenge in computer vision, aiming at reconstructing the dense depth map from a sparse one, typically with a paired RGB image. Existing learning based models rely on carefully prepared but limited data, leading to significant performance degradation in out-of-distribution (OOD) scenarios. Recent foundation models have demonstrated exceptional robustness in monocular depth estimation through large-scale training, and using such models to enhance the robustness of depth completion models is a promising solution. In this work, we propose a novel depth completion framework that leverages depth foundation models to attain remarkable robustness without large-scale training. Specifically, we leverage a depth foundation model to extract environmental cues, including structural and semantic context, from RGB images to guide the propagation of sparse depth information into missing regions. We further design a dual-space propagation approach, without any learnable parameters, to effectively propagates sparse depth in both 3D and 2D spaces to maintain geometric structure and local consistency. To refine the intricate structure, we introduce a learnable correction module to progressively adjust the depth prediction towards the real depth. We train our model on the NYUv2 and KITTI datasets as in-distribution datasets and extensively evaluate the framework on 16 other datasets. Our framework performs remarkably well in the OOD scenarios and outperforms existing state-of-the-art depth completion methods. Our models are released in https://github.com/shenglunch/PSD.

Jian Shi, Tianqi You, Pingping Zhang et al.

Automated and accurate segmentation of individual vertebra in 3D CT and MRI images is essential for various clinical applications. Due to the limitations of current imaging techniques and the complexity of spinal structures, existing methods still struggle with reducing the impact of image blurring and distinguishing similar vertebrae. To alleviate these issues, we introduce a Frequency-enhanced Multi-granularity Context Network (FMC-Net) to improve the accuracy of vertebrae segmentation. Specifically, we first apply wavelet transform for lossless downsampling to reduce the feature distortion in blurred images. The decomposed high and low-frequency components are then processed separately. For the high-frequency components, we apply a High-frequency Feature Refinement (HFR) to amplify the prominence of key features and filter out noises, restoring fine-grained details in blurred images. For the low-frequency components, we use a Multi-granularity State Space Model (MG-SSM) to aggregate feature representations with different receptive fields, extracting spatially-varying contexts while capturing long-range dependencies with linear complexity. The utilization of multi-granularity contexts is essential for distinguishing similar vertebrae and improving segmentation accuracy. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches on both CT and MRI vertebrae segmentation datasets. The source code is publicly available at https://github.com/anaanaa/FMCNet.

Chongwei Liu, Haojie Li, Zhihui Wang et al.

Recent advances in Multi-Object Tracking (MOT) have demonstrated significant success in short-term association within the separated tracking-by-detection online paradigm. However, long-term tracking remains challenging. While graph-based approaches address this by modeling trajectories as global graphs, these methods are unsuitable for real-time applications due to their non-online nature. In this paper, we review the concept of trajectory graphs and propose a novel perspective by representing them as directed acyclic graphs. This representation can be described using frame-ordered object sequences and binary adjacency matrices. We observe that this structure naturally aligns with Transformer attention mechanisms, enabling us to model the association problem using a classic Transformer architecture. Based on this insight, we introduce a concise Pure Transformer (PuTR) to validate the effectiveness of Transformer in unifying short- and long-term tracking for separated online MOT. Extensive experiments on four diverse datasets (SportsMOT, DanceTrack, MOT17, and MOT20) demonstrate that PuTR effectively establishes a solid baseline compared to existing foundational online methods while exhibiting superior domain adaptation capabilities. Furthermore, the separated nature enables efficient training and inference, making it suitable for practical applications. Implementation code and trained models are available at https://github.com/chongweiliu/PuTR .

Yixin Huang, Yiqi Jin, Ke Tao et al.

May-Thurner Syndrome (MTS) is a vascular condition that affects over 20\% of the population and significantly increases the risk of iliofemoral deep venous thrombosis. Accurate and early diagnosis of MTS using computed tomography (CT) remains a clinical challenge due to the subtle anatomical compression and variability across patients. In this paper, we propose MTS-Net, an end-to-end 3D deep learning framework designed to capture spatial-temporal patterns from CT volumes for reliable MTS diagnosis. MTS-Net builds upon 3D ResNet-18 by embedding a novel dual-enhanced positional multi-head self-attention (DEP-MHSA) module into the Transformer encoder of the network's final stages. The proposed DEP-MHSA employs multi-scale convolution and integrates positional embeddings into both attention weights and residual paths, enhancing spatial context preservation, which is crucial for identifying venous compression. To validate our approach, we curate the first publicly available dataset for MTS, MTS-CT, containing over 747 gender-balanced subjects with standard and enhanced CT scans. Experimental results demonstrate that MTS-Net achieves average 0.79 accuracy, 0.84 AUC, and 0.78 F1-score, outperforming baseline models including 3D ResNet, DenseNet-BC, and BabyNet. Our work not only introduces a new diagnostic architecture for MTS but also provides a high-quality benchmark dataset to facilitate future research in automated vascular syndrome detection. We make our code and dataset publicly available at:https://github.com/Nutingnon/MTS_dep_mhsa.

Zhiyu Chong, Xinzhu Ma, Hong Zhang et al.

3D object detection is a fundamental and challenging task for 3D scene understanding, and the monocular-based methods can serve as an economical alternative to the stereo-based or LiDAR-based methods. However, accurately detecting objects in the 3D space from a single image is extremely difficult due to the lack of spatial cues. To mitigate this issue, we propose a simple and effective scheme to introduce the spatial information from LiDAR signals to the monocular 3D detectors, without introducing any extra cost in the inference phase. In particular, we first project the LiDAR signals into the image plane and align them with the RGB images. After that, we use the resulting data to train a 3D detector (LiDAR Net) with the same architecture as the baseline model. Finally, this LiDAR Net can serve as the teacher to transfer the learned knowledge to the baseline model. Experimental results show that the proposed method can significantly boost the performance of the baseline model and ranks the $1^{st}$ place among all monocular-based methods on the KITTI benchmark. Besides, extensive ablation studies are conducted, which further prove the effectiveness of each part of our designs and illustrate what the baseline model has learned from the LiDAR Net. Our code will be released at \url{https://github.com/monster-ghost/MonoDistill}.

Zhiwei Ma, Haojie Li, Zhihui Wang et al.

With the development of underwater object grabbing technology, underwater object recognition and segmentation of high accuracy has become a challenge. The existing underwater object detection technology can only give the general position of an object, unable to give more detailed information such as the outline of the object, which seriously affects the grabbing efficiency. To address this problem, we label and establish the first underwater semantic segmentation dataset of real scene(DUT-USEG:DUT Underwater Segmentation Dataset). The DUT- USEG dataset includes 6617 images, 1487 of which have semantic segmentation and instance segmentation annotations, and the remaining 5130 images have object detection box annotations. Based on this dataset, we propose a semi-supervised underwater semantic segmentation network focusing on the boundaries(US-Net: Underwater Segmentation Network). By designing a pseudo label generator and a boundary detection subnetwork, this network realizes the fine learning of boundaries between underwater objects and background, and improves the segmentation effect of boundary areas. Experiments show that the proposed method improves by 6.7% in three categories of holothurian, echinus, starfish in DUT-USEG dataset, and achieves state-of-the-art results. The DUT- USEG dataset will be released at https://github.com/baxiyi/DUT-USEG.

Xinzhu Ma, Yinmin Zhang, Dan Xu et al.

Estimating 3D bounding boxes from monocular images is an essential component in autonomous driving, while accurate 3D object detection from this kind of data is very challenging. In this work, by intensive diagnosis experiments, we quantify the impact introduced by each sub-task and found the `localization error' is the vital factor in restricting monocular 3D detection. Besides, we also investigate the underlying reasons behind localization errors, analyze the issues they might bring, and propose three strategies. First, we revisit the misalignment between the center of the 2D bounding box and the projected center of the 3D object, which is a vital factor leading to low localization accuracy. Second, we observe that accurately localizing distant objects with existing technologies is almost impossible, while those samples will mislead the learned network. To this end, we propose to remove such samples from the training set for improving the overall performance of the detector. Lastly, we also propose a novel 3D IoU oriented loss for the size estimation of the object, which is not affected by `localization error'. We conduct extensive experiments on the KITTI dataset, where the proposed method achieves real-time detection and outperforms previous methods by a large margin. The code will be made available at: https://github.com/xinzhuma/monodle.

Hui Fu, Zeqing Wang, Ke Gong et al.

Speech-driven 3D facial animation aims to synthesize vivid facial animations that accurately synchronize with speech and match the unique speaking style. However, existing works primarily focus on achieving precise lip synchronization while neglecting to model the subject-specific speaking style, often resulting in unrealistic facial animations. To the best of our knowledge, this work makes the first attempt to explore the coupled information between the speaking style and the semantic content in facial motions. Specifically, we introduce an innovative speaking style disentanglement method, which enables arbitrary-subject speaking style encoding and leads to a more realistic synthesis of speech-driven facial animations. Subsequently, we propose a novel framework called \textbf{Mimic} to learn disentangled representations of the speaking style and content from facial motions by building two latent spaces for style and content, respectively. Moreover, to facilitate disentangled representation learning, we introduce four well-designed constraints: an auxiliary style classifier, an auxiliary inverse classifier, a content contrastive loss, and a pair of latent cycle losses, which can effectively contribute to the construction of the identity-related style space and semantic-related content space. Extensive qualitative and quantitative experiments conducted on three publicly available datasets demonstrate that our approach outperforms state-of-the-art methods and is capable of capturing diverse speaking styles for speech-driven 3D facial animation. The source code and supplementary video are publicly available at: https://zeqing-wang.github.io/Mimic/

Zeqing Wang, Qingyang Ma, Wentao Wan et al.

Recent improvements in visual synthesis have significantly enhanced the depiction of generated human photos, which are pivotal due to their wide applicability and demand. Nonetheless, the existing text-to-image or text-to-video models often generate low-quality human photos that might differ considerably from real-world body structures, referred to as "abnormal human bodies". Such abnormalities, typically deemed unacceptable, pose considerable challenges in the detection and repair of them within human photos. These challenges require precise abnormality recognition capabilities, which entail pinpointing both the location and the abnormality type. Intuitively, Visual Language Models (VLMs) that have obtained remarkable performance on various visual tasks are quite suitable for this task. However, their performance on abnormality detection in human photos is quite poor. Hence, it is quite important to highlight this task for the research community. In this paper, we first introduce a simple yet challenging task, i.e., \textbf{F}ine-grained \textbf{H}uman-body \textbf{A}bnormality \textbf{D}etection \textbf{(FHAD)}, and construct two high-quality datasets for evaluation. Then, we propose a meticulous framework, named HumanCalibrator, which identifies and repairs abnormalities in human body structures while preserving the other content. Experiments indicate that our HumanCalibrator achieves high accuracy in abnormality detection and accomplishes an increase in visual comparisons while preserving the other visual content.

Shijie Wang, Zijian Wang, Yadan Luo et al.

Ultra-fine-grained visual categorization (Ultra-FGVC) aims to classify highly similar subcategories within fine-grained objects using limited training samples. However, holistic yet discriminative cues, such as leaf contours in extremely similar cultivars, remain under-explored in current studies, thereby limiting recognition performance. Though crucial, modeling holistic cues with complex morphological structures typically requires massive training samples, posing significant challenges in data-limited scenarios. To address this challenge, we propose a novel Divide-and-Conquer Holistic Cognition Network (DHCNet) that implements a divide-and-conquer strategy by decomposing holistic cues into spatially-associated subtle discrepancies and progressively establishing the holistic cognition process, significantly simplifying holistic cognition while reducing dependency on training data. Technically, DHCNet begins by progressively analyzing subtle discrepancies, transitioning from smaller local patches to larger ones using a self-shuffling operation on local regions. Simultaneously, it leverages the unaffected local regions to potentially guide the perception of the original topological structure among the shuffled patches, thereby aiding in the establishment of spatial associations for these discrepancies. Additionally, DHCNet incorporates the online refinement of these holistic cues discovered from local regions into the training process to iteratively improve their quality. As a result, DHCNet uses these holistic cues as supervisory signals to fine-tune the parameters of the recognition model, thus improving its sensitivity to holistic cues across the entire objects. Extensive evaluations demonstrate that DHCNet achieves remarkable performance on five widely-used Ultra-FGVC datasets.

Shijie Wang, Yadan Luo, Zijian Wang et al.

This paper investigates the intrinsic geometrical features of highly similar objects and introduces a general self-supervised framework called the Geometric Attribute Exploration Network (GAEor), which is designed to address the ultra-fine-grained visual categorization (Ultra-FGVC) task in data-limited scenarios. Unlike prior work that often captures subtle yet critical distinctions, GAEor generates geometric attributes as novel alternative recognition cues. These attributes are determined by various details within the object, aligned with its geometric patterns, such as the intricate vein structures in soybean leaves. Crucially, each category exhibits distinct geometric descriptors that serve as powerful cues, even among objects with minimal visual variation -- a factor largely overlooked in recent research. GAEor discovers these geometric attributes by first amplifying geometry-relevant details via visual feedback from a backbone network, then embedding the relative polar coordinates of these details into the final representation. Extensive experiments demonstrate that GAEor significantly sets new state-of-the-art records in five widely-used Ultra-FGVC benchmarks.

Shengjie Gong, Haojie Li, Jiapeng Tang et al.

In this work, we introduce Monocular and Generalizable Gaussian Talking Head Animation (MGGTalk), which requires monocular datasets and generalizes to unseen identities without personalized re-training. Compared with previous 3D Gaussian Splatting (3DGS) methods that requires elusive multi-view datasets or tedious personalized learning/inference, MGGtalk enables more practical and broader applications. However, in the absence of multi-view and personalized training data, the incompleteness of geometric and appearance information poses a significant challenge. To address these challenges, MGGTalk explores depth information to enhance geometric and facial symmetry characteristics to supplement both geometric and appearance features. Initially, based on the pixel-wise geometric information obtained from depth estimation, we incorporate symmetry operations and point cloud filtering techniques to ensure a complete and precise position parameter for 3DGS. Subsequently, we adopt a two-stage strategy with symmetric priors for predicting the remaining 3DGS parameters. We begin by predicting Gaussian parameters for the visible facial regions of the source image. These parameters are subsequently utilized to improve the prediction of Gaussian parameters for the non-visible regions. Extensive experiments demonstrate that MGGTalk surpasses previous state-of-the-art methods, achieving superior performance across various metrics.

Jianman Lin, Haojie Li, Chunmei Qing et al.

General object composition (GOC) aims to seamlessly integrate a target object into a background scene with desired geometric properties, while simultaneously preserving its fine-grained appearance details. Recent approaches derive semantic embeddings and integrate them into advanced diffusion models to enable geometry-editable generation. However, these highly compact embeddings encode only high-level semantic cues and inevitably discard fine-grained appearance details. We introduce a Disentangled Geometry-editable and Appearance-preserving Diffusion (DGAD) model that first leverages semantic embeddings to implicitly capture the desired geometric transformations and then employs a cross-attention retrieval mechanism to align fine-grained appearance features with the geometry-edited representation, facilitating both precise geometry editing and faithful appearance preservation in object composition. Specifically, DGAD builds on CLIP/DINO-derived and reference networks to extract semantic embeddings and appearance-preserving representations, which are then seamlessly integrated into the encoding and decoding pipelines in a disentangled manner. We first integrate the semantic embeddings into pre-trained diffusion models that exhibit strong spatial reasoning capabilities to implicitly capture object geometry, thereby facilitating flexible object manipulation and ensuring effective editability. Then, we design a dense cross-attention mechanism that leverages the implicitly learned object geometry to retrieve and spatially align appearance features with their corresponding regions, ensuring faithful appearance consistency. Extensive experiments on public benchmarks demonstrate the effectiveness of the proposed DGAD framework.

Shijie Wang, Jian Shi, Haojie Li

Existing fine-grained image retrieval (FGIR) methods predominantly rely on supervision from predefined categories to learn discriminative representations for retrieving fine-grained objects. However, they inadvertently introduce category-specific semantics into the retrieval representation, creating semantic dependencies on predefined classes that critically hinder generalization to unseen categories. To tackle this, we propose AdvRF, a novel adversarial reconstruction feedback framework aimed at learning category-agnostic discrepancy representations. Specifically, AdvRF reformulates FGIR as a visual discrepancy reconstruction task via synergizing category-aware discrepancy localization from retrieval models with category-agnostic feature learning from reconstruction models. The reconstruction model exposes residual discrepancies overlooked by the retrieval model, forcing it to improve localization accuracy, while the refined signals from the retrieval model guide the reconstruction model to improve its reconstruction ability. Consequently, the retrieval model localizes visual differences, while the reconstruction model encodes these differences into category-agnostic representations. This representation is then transferred to the retrieval model through knowledge distillation for efficient deployment. Quantitative and qualitative evaluations demonstrate that our AdvRF achieves impressive performance on both widely-used fine-grained and coarse-grained datasets.

Zhizhen Zhang, Ning Wang, Haojie Li et al.

Semantic location prediction aims to derive meaningful location insights from multimodal social media posts, offering a more contextual understanding of daily activities than using GPS coordinates. This task faces significant challenges due to the noise and modality heterogeneity in "text-image" posts. Existing methods are generally constrained by inadequate feature representations and modal interaction, struggling to effectively reduce noise and modality heterogeneity. To address these challenges, we propose a Similarity-Guided Multimodal Fusion Transformer (SG-MFT) for predicting the semantic locations of users from their multimodal posts. First, we incorporate high-quality text and image representations by utilizing a pre-trained large vision-language model. Then, we devise a Similarity-Guided Interaction Module (SIM) to alleviate modality heterogeneity and noise interference by incorporating both coarse-grained and fine-grained similarity guidance for improving modality interactions. Specifically, we propose a novel similarity-aware feature interpolation attention mechanism at the coarse-grained level, leveraging modality-wise similarity to mitigate heterogeneity and reduce noise within each modality. At the fine-grained level, we utilize a similarity-aware feed-forward block and element-wise similarity to further address the issue of modality heterogeneity. Finally, building upon pre-processed features with minimal noise and modal interference, we devise a Similarity-aware Fusion Module (SFM) to fuse two modalities with a cross-attention mechanism. Comprehensive experimental results clearly demonstrate the superior performance of our proposed method.

Bruce X. B. Yu, Jianlong Chang, Haixin Wang et al.

Fine-tuning visual models has been widely shown promising performance on many downstream visual tasks. With the surprising development of pre-trained visual foundation models, visual tuning jumped out of the standard modus operandi that fine-tunes the whole pre-trained model or just the fully connected layer. Instead, recent advances can achieve superior performance than full-tuning the whole pre-trained parameters by updating far fewer parameters, enabling edge devices and downstream applications to reuse the increasingly large foundation models deployed on the cloud. With the aim of helping researchers get the full picture and future directions of visual tuning, this survey characterizes a large and thoughtful selection of recent works, providing a systematic and comprehensive overview of existing work and models. Specifically, it provides a detailed background of visual tuning and categorizes recent visual tuning techniques into five groups: prompt tuning, adapter tuning, parameter tuning, and remapping tuning. Meanwhile, it offers some exciting research directions for prospective pre-training and various interactions in visual tuning.

Chongwei Liu, Haojie Li, Shuchang Wang et al.

Underwater object detection for robot picking has attracted a lot of interest. However, it is still an unsolved problem due to several challenges. We take steps towards making it more realistic by addressing the following challenges. Firstly, the currently available datasets basically lack the test set annotations, causing researchers must compare their method with other SOTAs on a self-divided test set (from the training set). Training other methods lead to an increase in workload and different researchers divide different datasets, resulting there is no unified benchmark to compare the performance of different algorithms. Secondly, these datasets also have other shortcomings, e.g., too many similar images or incomplete labels. Towards these challenges we introduce a dataset, Detecting Underwater Objects (DUO), and a corresponding benchmark, based on the collection and re-annotation of all relevant datasets. DUO contains a collection of diverse underwater images with more rational annotations. The corresponding benchmark provides indicators of both efficiency and accuracy of SOTAs (under the MMDtection framework) for academic research and industrial applications, where JETSON AGX XAVIER is used to assess detector speed to simulate the robot-embedded environment.

Baoli Sun, Xinchen Ye, Baopu Li et al.

Existing color-guided depth super-resolution (DSR) approaches require paired RGB-D data as training samples where the RGB image is used as structural guidance to recover the degraded depth map due to their geometrical similarity. However, the paired data may be limited or expensive to be collected in actual testing environment. Therefore, we explore for the first time to learn the cross-modality knowledge at training stage, where both RGB and depth modalities are available, but test on the target dataset, where only single depth modality exists. Our key idea is to distill the knowledge of scene structural guidance from RGB modality to the single DSR task without changing its network architecture. Specifically, we construct an auxiliary depth estimation (DE) task that takes an RGB image as input to estimate a depth map, and train both DSR task and DE task collaboratively to boost the performance of DSR. Upon this, a cross-task interaction module is proposed to realize bilateral cross task knowledge transfer. First, we design a cross-task distillation scheme that encourages DSR and DE networks to learn from each other in a teacher-student role-exchanging fashion. Then, we advance a structure prediction (SP) task that provides extra structure regularization to help both DSR and DE networks learn more informative structure representations for depth recovery. Extensive experiments demonstrate that our scheme achieves superior performance in comparison with other DSR methods.

Wei Wang, Baopu Li, Shuhui Yang et al.

Domain adaptation has received a lot of attention in recent years, and many algorithms have been proposed with impressive progress. However, it is still not fully explored concerning the joint probability distribution (P(X, Y)) distance for this problem, since its empirical estimation derived from the maximum mean discrepancy (joint maximum mean discrepancy, JMMD) will involve complex tensor-product operator that is hard to manipulate. To solve this issue, this paper theoretically derives a unified form of JMMD that is easy to optimize, and proves that the marginal, class conditional and weighted class conditional probability distribution distances are our special cases with different label kernels, among which the weighted class conditional one not only can realize feature alignment across domains in the category level, but also deal with imbalance dataset using the class prior probabilities. From the revealed unified JMMD, we illustrate that JMMD degrades the feature-label dependence (discriminability) that benefits to classification, and it is sensitive to the label distribution shift when the label kernel is the weighted class conditional one. Therefore, we leverage Hilbert Schmidt independence criterion and propose a novel MMD matrix to promote the dependence, and devise a novel label kernel that is robust to label distribution shift. Finally, we conduct extensive experiments on several cross-domain datasets to demonstrate the validity and effectiveness of the revealed theoretical results.

Hong Zhang, Shenglun Chen, Zhihui Wang et al.

A Multistage Full Matching disparity estimation scheme (MFM) is proposed in this work. We demonstrate that decouple all similarity scores directly from the low-resolution 4D volume step by step instead of estimating low-resolution 3D cost volume through focusing on optimizing the low-resolution 4D volume iteratively leads to more accurate disparity. To this end, we first propose to decompose the full matching task into multiple stages of the cost aggregation module. Specifically, we decompose the high-resolution predicted results into multiple groups, and every stage of the newly designed cost aggregation module learns only to estimate the results for a group of points. This alleviates the problem of feature internal competitive when learning similarity scores of all candidates from one low-resolution 4D volume output from one stage. Then, we propose the strategy of \emph{Stages Mutual Aid}, which takes advantage of the relationship of multiple stages to boost similarity scores estimation of each stage, to solve the unbalanced prediction of multiple stages caused by serial multistage framework. Experiment results demonstrate that the proposed method achieves more accurate disparity estimation results and outperforms state-of-the-art methods on Scene Flow, KITTI 2012 and KITTI 2015 datasets.

Hong Zhang, Haojie Li, Shenglun Chen et al.

Being a crucial task of autonomous driving, Stereo matching has made great progress in recent years. Existing stereo matching methods estimate disparity instead of depth. They treat the disparity errors as the evaluation metric of the depth estimation errors, since the depth can be calculated from the disparity according to the triangulation principle. However, we find that the error of the depth depends not only on the error of the disparity but also on the depth range of the points. Therefore, even if the disparity error is low, the depth error is still large, especially for the distant points. In this paper, a novel Direct Depth Learning Network (DDL-Net) is designed for stereo matching. DDL-Net consists of two stages: the Coarse Depth Estimation stage and the Adaptive-Grained Depth Refinement stage, which are all supervised by depth instead of disparity. Specifically, Coarse Depth Estimation stage uniformly samples the matching candidates according to depth range to construct cost volume and output coarse depth. Adaptive-Grained Depth Refinement stage performs further matching near the coarse depth to correct the imprecise matching and wrong matching. To make the Adaptive-Grained Depth Refinement stage robust to the coarse depth and adaptive to the depth range of the points, the Granularity Uncertainty is introduced to Adaptive-Grained Depth Refinement stage. Granularity Uncertainty adjusts the matching range and selects the candidates' features according to coarse prediction confidence and depth range. We verify the performance of DDL-Net on SceneFlow dataset and DrivingStereo dataset by different depth metrics. Results show that DDL-Net achieves an average improvement of 25% on the SceneFlow dataset and $12\%$ on the DrivingStereo dataset comparing the classical methods. More importantly, we achieve state-of-the-art accuracy at a large distance.

Peiyao Wang, Weixin Luo, Yanyu Xu et al.

Spatial Description Resolution, as a language-guided localization task, is proposed for target location in a panoramic street view, given corresponding language descriptions. Explicitly characterizing an object-level relationship while distilling spatial relationships are currently absent but crucial to this task. Mimicking humans, who sequentially traverse spatial relationship words and objects with a first-person view to locate their target, we propose a novel spatial relationship induced (SIRI) network. Specifically, visual features are firstly correlated at an implicit object-level in a projected latent space; then they are distilled by each spatial relationship word, resulting in each differently activated feature representing each spatial relationship. Further, we introduce global position priors to fix the absence of positional information, which may result in global positional reasoning ambiguities. Both the linguistic and visual features are concatenated to finalize the target localization. Experimental results on the Touchdown show that our method is around 24\% better than the state-of-the-art method in terms of accuracy, measured by an 80-pixel radius. Our method also generalizes well on our proposed extended dataset collected using the same settings as Touchdown.

Wei Wang, Haojie Li, Zhengming Ding et al.

Existing domain adaptation methods aim to reduce the distributional difference between the source and target domains and respect their specific discriminative information, by establishing the Maximum Mean Discrepancy (MMD) and the discriminative distances. However, they usually accumulate to consider those statistics and deal with their relationships by estimating parameters blindly. This paper theoretically proves two essential facts: 1) minimizing the MMD equals to maximize the source and target intra-class distances respectively but jointly minimize their variance with some implicit weights, so that the feature discriminability degrades; 2) the relationship between the intra-class and inter-class distances is as one falls, another rises. Based on this, we propose a novel discriminative MMD. On one hand, we consider the intra-class and inter-class distances alone to remove a redundant parameter, and the revealed weights provide their approximate optimal ranges. On the other hand, we design two different strategies to boost the feature discriminability: 1) we directly impose a trade-off parameter on the implicit intra-class distance in MMD to regulate its change; 2) we impose the similar weights revealed in MMD on inter-class distance and maximize it, then a balanced factor could be introduced to quantitatively leverage the relative importance between the feature transferability and its discriminability. The experiments on several benchmark datasets not only prove the validity of theoretical results but also demonstrate that our approach could perform better than the comparative state-of-art methods substantially.

Wei Wang, Zhihui Wang, Yuankai Xiang et al.

Domain Adaptation (DA) aims to generalize the classifier learned from the source domain to the target domain. Existing DA methods usually assume that rich labels could be available in the source domain. However, there are usually a large number of unlabeled data but only a few labeled data in the source domain, and how to transfer knowledge from this sparsely-labeled source domain to the target domain is still a challenge, which greatly limits their application in the wild. This paper proposes a novel Sparsely-Labeled Source Assisted Domain Adaptation (SLSA-DA) algorithm to address the challenge with limited labeled source domain samples. Specifically, due to the label scarcity problem, the projected clustering is conducted on both the source and target domains, so that the discriminative structures of data could be leveraged elegantly. Then the label propagation is adopted to propagate the labels from those limited labeled source samples to the whole unlabeled data progressively, so that the cluster labels are revealed correctly. Finally, we jointly align the marginal and conditional distributions to mitigate the cross-domain mismatch problem, and optimize those three procedures iteratively. However, it is nontrivial to incorporate those three procedures into a unified optimization framework seamlessly since some variables to be optimized are implicitly involved in their formulas, thus they could not promote to each other. Remarkably, we prove that the projected clustering and conditional distribution alignment could be reformulated as different expressions, thus the implicit variables are revealed in different optimization steps. As such, the variables related to those three quantities could be optimized in a unified optimization framework and facilitate to each other, to improve the recognition performance obviously.

Zengyuan Guo, Zilin Wang, Zhihui Wang et al.

Regression-based text detection methods have already achieved promising performances with simple network structure and high efficiency. However, they are behind in accuracy comparing with recent segmentation-based text detectors. In this work, we discover that one important reason to this case is that regression-based methods usually utilize a fixed feature selection way, i.e. selecting features in a single location or in neighbor regions, to predict components of the bounding box, such as the distances to the boundaries or the rotation angle. The features selected through this way sometimes are not the best choices for predicting every component of a text bounding box and thus degrade the accuracy performance. To address this issue, we propose a novel Location-Aware feature Selection text detection Network (LASNet). LASNet selects suitable features from different locations to separately predict the five components of a bounding box and gets the final bounding box through the combination of these components. Specifically, instead of using the classification score map to select one feature for predicting the whole bounding box as most of the existing methods did, the proposed LASNet first learn five new confidence score maps to indicate the prediction accuracy of the bounding box components, respectively. Then, a Location-Aware Feature Selection mechanism (LAFS) is designed to weightily fuse the top-$K$ prediction results for each component according to their confidence score, and to combine the all five fused components into a final bounding box. As a result, LASNet predicts the more accurate bounding boxes by using a learnable feature selection way. The experimental results demonstrate that our LASNet achieves state-of-the-art performance with single-model and single-scale testing, outperforming all existing regression-based detectors.

Chongwei Liu, Zhihui Wang, Shijie Wang et al.

To boost the object grabbing capability of underwater robots for open-sea farming, we propose a new dataset (UDD) consisting of three categories (seacucumber, seaurchin, and scallop) with 2,227 images. To the best of our knowledge, it is the first 4K HD dataset collected in a real open-sea farm. We also propose a novel Poisson-blending Generative Adversarial Network (Poisson GAN) and an efficient object detection network (AquaNet) to address two common issues within related datasets: the class-imbalance problem and the problem of mass small object, respectively. Specifically, Poisson GAN combines Poisson blending into its generator and employs a new loss called Dual Restriction loss (DR loss), which supervises both implicit space features and image-level features during training to generate more realistic images. By utilizing Poisson GAN, objects of minority class like seacucumber or scallop could be added into an image naturally and annotated automatically, which could increase the loss of minority classes during training detectors to eliminate the class-imbalance problem; AquaNet is a high-efficiency detector to address the problem of detecting mass small objects from cloudy underwater pictures. Within it, we design two efficient components: a depth-wise-convolution-based Multi-scale Contextual Features Fusion (MFF) block and a Multi-scale Blursampling (MBP) module to reduce the parameters of the network to 1.3 million. Both two components could provide multi-scale features of small objects under a short backbone configuration without any loss of accuracy. In addition, we construct a large-scale augmented dataset (AUDD) and a pre-training dataset via Poisson GAN from UDD. Extensive experiments show the effectiveness of the proposed Poisson GAN, AquaNet, UDD, AUDD, and pre-training dataset.

Wei Wang, Haojie Li, Zhihui Wang et al.

In Domain Adaptation (DA), the category-relevant losses usually occupy a dominant position, while they are usually built with hard or soft labels in existing models. We observed that hard labels are overconfident due to hard samples existed, and soft labels are ambiguous as too many small noisy probabilities involved, and both of them are easily to cause negative transfer. Besides, the category-irrelevant losses in Closed-Set DA (CSDA) paradigm fail to work in Open-Set DA (OSDA), and they also have to be in a category-relevant form, since target data samples are split into shared and private classes. To this end, we propose a newly-unified DA framework (i.e., Importance Filtered Cross-Domain Adaptation, IFCDA). Firstly, an importance filtered mechanism is devised to generate filtered soft labels to mitigate negative transfer desirably. Specifically, the soft labels are divided into confident and ambiguous ones. Then, only the maximum probability in each confident label is retained, and a threshold value is set to truncate each ambiguous label so that only prominent probabilities are reserved. Moreover, a general graph-based label propagation is contrived to attain soft labels in both CSDA and OSDA, where an extra component is embedded into label vector, so that it could detect target novel classes. Finally, the category-relevant losses in both scenarios are reformulated using filtered soft labels, while the category-irrelevant MMD loss in CSDA is reformulated as a form like class-wise MMD using newly-designed importance filtered soft labels. Notably, CSDA paradigm is a special case when all extra components are set to 0, thus the proposed approach is geared to both CSDA and OSDA. Comprehensive experiments on benchmark cross-domain object recognition datasets verify that the proposed approach outperforms several state-of-the-art methods in both scenarios.

Xinzhu Ma, Zhihui Wang, Haojie Li et al.

In this paper, we propose a monocular 3D object detection framework in the domain of autonomous driving. Unlike previous image-based methods which focus on RGB feature extracted from 2D images, our method solves this problem in the reconstructed 3D space in order to exploit 3D contexts explicitly. To this end, we first leverage a stand-alone module to transform the input data from 2D image plane to 3D point clouds space for a better input representation, then we perform the 3D detection using PointNet backbone net to obtain objects 3D locations, dimensions and orientations. To enhance the discriminative capability of point clouds, we propose a multi-modal feature fusion module to embed the complementary RGB cue into the generated point clouds representation. We argue that it is more effective to infer the 3D bounding boxes from the generated 3D scene space (i.e., X,Y, Z space) compared to the image plane (i.e., R,G,B image plane). Evaluation on the challenging KITTI dataset shows that our approach boosts the performance of state-of-the-art monocular approach by a large margin.

Yuanzheng Ci, Xinzhu Ma, Zhihui Wang et al.

Scribble colors based line art colorization is a challenging computer vision problem since neither greyscale values nor semantic information is presented in line arts, and the lack of authentic illustration-line art training pairs also increases difficulty of model generalization. Recently, several Generative Adversarial Nets (GANs) based methods have achieved great success. They can generate colorized illustrations conditioned on given line art and color hints. However, these methods fail to capture the authentic illustration distributions and are hence perceptually unsatisfying in the sense that they often lack accurate shading. To address these challenges, we propose a novel deep conditional adversarial architecture for scribble based anime line art colorization. Specifically, we integrate the conditional framework with WGAN-GP criteria as well as the perceptual loss to enable us to robustly train a deep network that makes the synthesized images more natural and real. We also introduce a local features network that is independent of synthetic data. With GANs conditioned on features from such network, we notably increase the generalization capability over "in the wild" line arts. Furthermore, we collect two datasets that provide high-quality colorful illustrations and authentic line arts for training and benchmarking. With the proposed model trained on our illustration dataset, we demonstrate that images synthesized by the presented approach are considerably more realistic and precise than alternative approaches.

Qi Yuan, Bingwang Zhang, Haojie Li et al.

Currently, most top-performing text detection networks tend to employ fixed-size anchor boxes to guide the search for text instances. They usually rely on a large amount of anchors with different scales to discover texts in scene images, thus leading to high computational cost. In this paper, we propose an end-to-end box-based text detector with scale-adaptive anchors, which can dynamically adjust the scales of anchors according to the sizes of underlying texts by introducing an additional scale regression layer. The proposed scale-adaptive anchors allow us to use a few number of anchors to handle multi-scale texts and therefore significantly improve the computational efficiency. Moreover, compared to discrete scales used in previous methods, the learned continuous scales are more reliable, especially for small texts detection. Additionally, we propose Anchor convolution to better exploit necessary feature information by dynamically adjusting the sizes of receptive fields according to the learned scales. Extensive experiments demonstrate that the proposed detector is fast, taking only $0.28$ second per image, while outperforming most state-of-the-art methods in accuracy.

Qi Jia, Meiyu Yu, Xin Fan et al.

Recognizing freehand sketches with high arbitrariness is greatly challenging. Most existing methods either ignore the geometric characteristics or treat sketches as handwritten characters with fixed structural ordering. Consequently, they can hardly yield high recognition performance even though sophisticated learning techniques are employed. In this paper, we propose a sequential deep learning strategy that combines both shape and texture features. A coded shape descriptor is exploited to characterize the geometry of sketch strokes with high flexibility, while the outputs of constitutional neural networks (CNN) are taken as the abstract texture feature. We develop dual deep networks with memorable gated recurrent units (GRUs), and sequentially feed these two types of features into the dual networks, respectively. These dual networks enable the feature fusion by another gated recurrent unit (GRU), and thus accurately recognize sketches invariant to stroke ordering. The experiments on the TU-Berlin data set show that our method outperforms the average of human and state-of-the-art algorithms even when significant shape and appearance variations occur.