Pengfei Zhu

Qinghe Wang, Lijie Liu, Miao Hua et al.

Image-based head swapping task aims to stitch a source head to another source body flawlessly. This seldom-studied task faces two major challenges: 1) Preserving the head and body from various sources while generating a seamless transition region. 2) No paired head swapping dataset and benchmark so far. In this paper, we propose a semantic-mixing diffusion model for head swapping (HS-Diffusion) which consists of a latent diffusion model (LDM) and a semantic layout generator. We blend the semantic layouts of source head and source body, and then inpaint the transition region by the semantic layout generator, achieving a coarse-grained head swapping. Semantic-mixing LDM can further implement a fine-grained head swapping with the inpainted layout as condition by a progressive fusion process, while preserving head and body with high-quality reconstruction. To this end, we propose a semantic calibration strategy for natural inpainting and a neck alignment for geometric realism. Importantly, we construct a new image-based head swapping benchmark and design two tailor-designed metrics (Mask-FID and Focal-FID). Extensive experiments demonstrate the superiority of our framework. The code will be available: https://github.com/qinghew/HS-Diffusion.

Yiming Sun, Bing Cao, Pengfei Zhu et al.

Infrared and visible image fusion aims to integrate comprehensive information from multiple sources to achieve superior performances on various practical tasks, such as detection, over that of a single modality. However, most existing methods directly combined the texture details and object contrast of different modalities, ignoring the dynamic changes in reality, which diminishes the visible texture in good lighting conditions and the infrared contrast in low lighting conditions. To fill this gap, we propose a dynamic image fusion framework with a multi-modal gated mixture of local-to-global experts, termed MoE-Fusion, to dynamically extract effective and comprehensive information from the respective modalities. Our model consists of a Mixture of Local Experts (MoLE) and a Mixture of Global Experts (MoGE) guided by a multi-modal gate. The MoLE performs specialized learning of multi-modal local features, prompting the fused images to retain the local information in a sample-adaptive manner, while the MoGE focuses on the global information that complements the fused image with overall texture detail and contrast. Extensive experiments show that our MoE-Fusion outperforms state-of-the-art methods in preserving multi-modal image texture and contrast through the local-to-global dynamic learning paradigm, and also achieves superior performance on detection tasks. Our code will be available: https://github.com/SunYM2020/MoE-Fusion.

Wei Shang, Dongwei Ren, Wanying Zhang et al.

Modern consumer cameras commonly employ the rolling shutter (RS) imaging mechanism, via which images are captured by scanning scenes row-by-row, resulting in RS distortion for dynamic scenes. To correct RS distortion, existing methods adopt a fully supervised learning manner that requires high framerate global shutter (GS) images as ground-truth for supervision. In this paper, we propose an enhanced Self-supervised learning framework for Dual reversed RS distortion Correction (SelfDRSC++). Firstly, we introduce a lightweight DRSC network that incorporates a bidirectional correlation matching block to refine the joint optimization of optical flows and corrected RS features, thereby improving correction performance while reducing network parameters. Subsequently, to effectively train the DRSC network, we propose a self-supervised learning strategy that ensures cycle consistency between input and reconstructed dual reversed RS images. The RS reconstruction in SelfDRSC++ can be interestingly formulated as a specialized instance of video frame interpolation, where each row in reconstructed RS images is interpolated from predicted GS images by utilizing RS distortion time maps. By achieving superior performance while simplifying the training process, SelfDRSC++ enables feasible one-stage self-supervised training. Additionally, besides start and end RS scanning time, SelfDRSC++ allows supervision of GS images at arbitrary intermediate scanning times, thus enabling the learned DRSC network to generate high framerate GS videos. The code and trained models are available at \url{https://github.com/shangwei5/SelfDRSC_plusplus}.

Junwen Pan, Pengfei Zhu, Kaihua Zhang et al.

Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention recently. Most leading WSSS methods employ a sophisticated multi-stage training strategy to estimate pseudo-labels as precise as possible, but they suffer from high model complexity. In contrast, there exists another research line that trains a single network with image-level labels in one training cycle. However, such a single-stage strategy often performs poorly because of the compounding effect caused by inaccurate pseudo-label estimation. To address this issue, this paper presents a Self-supervised Low-Rank Network (SLRNet) for single-stage WSSS and SSSS. The SLRNet uses cross-view self-supervision, that is, it simultaneously predicts several complementary attentive LR representations from different views of an image to learn precise pseudo-labels. Specifically, we reformulate the LR representation learning as a collective matrix factorization problem and optimize it jointly with the network learning in an end-to-end manner. The resulting LR representation deprecates noisy information while capturing stable semantics across different views, making it robust to the input variations, thereby reducing overfitting to self-supervision errors. The SLRNet can provide a unified single-stage framework for various label-efficient semantic segmentation settings: 1) WSSS with image-level labeled data, 2) SSSS with a few pixel-level labeled data, and 3) SSSS with a few pixel-level labeled data and many image-level labeled data. Extensive experiments on the Pascal VOC 2012, COCO, and L2ID datasets demonstrate that our SLRNet outperforms both state-of-the-art WSSS and SSSS methods with a variety of different settings, proving its good generalizability and efficacy.

Wei Shang, Wanying Zhang, Shuhang Gu et al.

Arbitrary-scale video super-resolution (AVSR) aims to enhance the resolution of video frames, potentially at various scaling factors, which presents several challenges regarding spatial detail reproduction, temporal consistency, and computational complexity. In this paper, we propose a strong baseline BasicAVSR for AVSR by integrating four key components: 1) adaptive multi-scale frequency priors generated from image Laplacian pyramids, 2) a flow-guided propagation unit to aggregate spatiotemporal information from adjacent frames, 3) a second-order motion compensation unit for more accurate spatial alignment of adjacent frames, and 4) a hyper-upsampling unit to generate scale-aware and content-independent upsampling kernels. To meet diverse application demands, we instantiate three propagation variants: (i) a unidirectional RNN unit for strictly online inference, (ii) a unidirectional RNN unit empowered with a limited lookahead that tolerates a small output delay, and (iii) a bidirectional RNN unit designed for offline tasks where computational resources are less constrained. Experimental results demonstrate the effectiveness and adaptability of our model across these different scenarios. Through extensive experiments, we show that BasicAVSR significantly outperforms existing methods in terms of super-resolution quality, generalization ability, and inference speed. Our work not only advances the state-of-the-art in AVSR but also extends its core components to multiple frameworks for diverse scenarios. The code is available at https://github.com/shangwei5/BasicAVSR.

Pengfei Zhu, Xinjie Yao, Yu Wang et al.

Multi-view learning has progressed rapidly in recent years. Although many previous studies assume that each instance appears in all views, it is common in real-world applications for instances to be missing from some views, resulting in incomplete multi-view data. To tackle this problem, we propose a novel Latent Heterogeneous Graph Network (LHGN) for incomplete multi-view learning, which aims to use multiple incomplete views as fully as possible in a flexible manner. By learning a unified latent representation, a trade-off between consistency and complementarity among different views is implicitly realized. To explore the complex relationship between samples and latent representations, a neighborhood constraint and a view-existence constraint are proposed, for the first time, to construct a heterogeneous graph. Finally, to avoid any inconsistencies between training and test phase, a transductive learning technique is applied based on graph learning for classification tasks. Extensive experimental results on real-world datasets demonstrate the effectiveness of our model over existing state-of-the-art approaches.

Xiaoran Fan, Chao Pang, Tian Yuan et al. · apple-ml

Speech representation learning has improved both speech understanding and speech synthesis tasks for single language. However, its ability in cross-lingual scenarios has not been explored. In this paper, we extend the pretraining method for cross-lingual multi-speaker speech synthesis tasks, including cross-lingual multi-speaker voice cloning and cross-lingual multi-speaker speech editing. We propose a speech-text joint pretraining framework, where we randomly mask the spectrogram and the phonemes given a speech example and its transcription. By learning to reconstruct the masked parts of the input in different languages, our model shows great improvements over speaker-embedding-based multi-speaker TTS methods. Moreover, our framework is end-to-end for both the training and the inference without any finetuning effort. In cross-lingual multi-speaker voice cloning and cross-lingual multi-speaker speech editing tasks, our experiments show that our model outperforms speaker-embedding-based multi-speaker TTS methods.

Pengfei Zhu, Chao Pang, Yekun Chai et al.

In recent years, the burgeoning interest in diffusion models has led to significant advances in image and speech generation. Nevertheless, the direct synthesis of music waveforms from unrestricted textual prompts remains a relatively underexplored domain. In response to this lacuna, this paper introduces a pioneering contribution in the form of a text-to-waveform music generation model, underpinned by the utilization of diffusion models. Our methodology hinges on the innovative incorporation of free-form textual prompts as conditional factors to guide the waveform generation process within the diffusion model framework. Addressing the challenge of limited text-music parallel data, we undertake the creation of a dataset by harnessing web resources, a task facilitated by weak supervision techniques. Furthermore, a rigorous empirical inquiry is undertaken to contrast the efficacy of two distinct prompt formats for text conditioning, namely, music tags and unconstrained textual descriptions. The outcomes of this comparative analysis affirm the superior performance of our proposed model in terms of enhancing text-music relevance. Finally, our work culminates in a demonstrative exhibition of the excellent capabilities of our model in text-to-music generation. We further demonstrate that our generated music in the waveform domain outperforms previous works by a large margin in terms of diversity, quality, and text-music relevance.

Junwen Pan, Qi Bi, Yanzhan Yang et al.

Due to the lack of expertise for medical image annotation, the investigation of label-efficient methodology for medical image segmentation becomes a heated topic. Recent progresses focus on the efficient utilization of weak annotations together with few strongly-annotated labels so as to achieve comparable segmentation performance in many unprofessional scenarios. However, these approaches only concentrate on the supervision inconsistency between strongly- and weakly-annotated instances but ignore the instance inconsistency inside the weakly-annotated instances, which inevitably leads to performance degradation. To address this problem, we propose a novel label-efficient hybrid-supervised framework, which considers each weakly-annotated instance individually and learns its weight guided by the gradient direction of the strongly-annotated instances, so that the high-quality prior in the strongly-annotated instances is better exploited and the weakly-annotated instances are depicted more precisely. Specially, our designed dynamic instance indicator (DII) realizes the above objectives, and is adapted to our dynamic co-regularization (DCR) framework further to alleviate the erroneous accumulation from distortions of weak annotations. Extensive experiments on two hybrid-supervised medical segmentation datasets demonstrate that with only 10% strong labels, the proposed framework can leverage the weak labels efficiently and achieve competitive performance against the 100% strong-label supervised scenario.

Pengfei Zhu, Mengshi Qi, Xia Li et al.

Predicting attention regions of interest is an important yet challenging task for self-driving systems. Existing methodologies rely on large-scale labeled traffic datasets that are labor-intensive to obtain. Besides, the huge domain gap between natural scenes and traffic scenes in current datasets also limits the potential for model training. To address these challenges, we are the first to introduce an unsupervised way to predict self-driving attention by uncertainty modeling and driving knowledge integration. Our approach's Uncertainty Mining Branch (UMB) discovers commonalities and differences from multiple generated pseudo-labels achieved from models pre-trained on natural scenes by actively measuring the uncertainty. Meanwhile, our Knowledge Embedding Block (KEB) bridges the domain gap by incorporating driving knowledge to adaptively refine the generated pseudo-labels. Quantitative and qualitative results with equivalent or even more impressive performance compared to fully-supervised state-of-the-art approaches across all three public datasets demonstrate the effectiveness of the proposed method and the potential of this direction. The code will be made publicly available.

Mingze Gao, Qilong Wang, Zhenyi Lin et al.

Recently, efficient fine-tuning of large-scale pre-trained models has attracted increasing research interests, where linear probing (LP) as a fundamental module is involved in exploiting the final representations for task-dependent classification. However, most of the existing methods focus on how to effectively introduce a few of learnable parameters, and little work pays attention to the commonly used LP module. In this paper, we propose a novel Moment Probing (MP) method to further explore the potential of LP. Distinguished from LP which builds a linear classification head based on the mean of final features (e.g., word tokens for ViT) or classification tokens, our MP performs a linear classifier on feature distribution, which provides the stronger representation ability by exploiting richer statistical information inherent in features. Specifically, we represent feature distribution by its characteristic function, which is efficiently approximated by using first- and second-order moments of features. Furthermore, we propose a multi-head convolutional cross-covariance (MHC$^3$) to compute second-order moments in an efficient and effective manner. By considering that MP could affect feature learning, we introduce a partially shared module to learn two recalibrating parameters (PSRP) for backbones based on MP, namely MP$_{+}$. Extensive experiments on ten benchmarks using various models show that our MP significantly outperforms LP and is competitive with counterparts at less training cost, while our MP$_{+}$ achieves state-of-the-art performance.

Junwen Pan, Guanlin Chen, Yi Liu et al.

Answer grounding aims to reveal the visual evidence for visual question answering (VQA), which entails highlighting relevant positions in the image when answering questions about images. Previous attempts typically tackle this problem using pretrained object detectors, but without the flexibility for objects not in the predefined vocabulary. However, these black-box methods solely concentrate on the linguistic generation, ignoring the visual interpretability. In this paper, we propose Dual Visual-Linguistic Interaction (DaVI), a novel unified end-to-end framework with the capability for both linguistic answering and visual grounding. DaVI innovatively introduces two visual-linguistic interaction mechanisms: 1) visual-based linguistic encoder that understands questions incorporated with visual features and produces linguistic-oriented evidence for further answer decoding, and 2) linguistic-based visual decoder that focuses visual features on the evidence-related regions for answer grounding. This way, our approach ranked the 1st place in the answer grounding track of 2022 VizWiz Grand Challenge.

Bing Cao, Junliang Guo, Pengfei Zhu et al.

Due to the rapid development of computer vision, single-modal (RGB) object tracking has made significant progress in recent years. Considering the limitation of single imaging sensor, multi-modal images (RGB, Infrared, etc.) are introduced to compensate for this deficiency for all-weather object tracking in complex environments. However, as acquiring sufficient multi-modal tracking data is hard while the dominant modality changes with the open environment, most existing techniques fail to extract multi-modal complementary information dynamically, yielding unsatisfactory tracking performance. To handle this problem, we propose a novel multi-modal visual prompt tracking model based on a universal bi-directional adapter, cross-prompting multiple modalities mutually. Our model consists of a universal bi-directional adapter and multiple modality-specific transformer encoder branches with sharing parameters. The encoders extract features of each modality separately by using a frozen pre-trained foundation model. We develop a simple but effective light feature adapter to transfer modality-specific information from one modality to another, performing visual feature prompt fusion in an adaptive manner. With adding fewer (0.32M) trainable parameters, our model achieves superior tracking performance in comparison with both the full fine-tuning methods and the prompt learning-based methods. Our code is available: https://github.com/SparkTempest/BAT.

Pengfei Zhu, Qian Wang, Yu Wang et al.

Attributed graph clustering is an unsupervised task that partitions nodes into different groups. Self-supervised learning (SSL) shows great potential in handling this task, and some recent studies simultaneously learn multiple SSL tasks to further boost performance. Currently, different SSL tasks are assigned the same set of weights for all graph nodes. However, we observe that some graph nodes whose neighbors are in different groups require significantly different emphases on SSL tasks. In this paper, we propose to dynamically learn the weights of SSL tasks for different nodes and fuse the embeddings learned from different SSL tasks to boost performance. We design an innovative graph clustering approach, namely Dynamically Fusing Self-Supervised Learning (DyFSS). Specifically, DyFSS fuses features extracted from diverse SSL tasks using distinct weights derived from a gating network. To effectively learn the gating network, we design a dual-level self-supervised strategy that incorporates pseudo labels and the graph structure. Extensive experiments on five datasets show that DyFSS outperforms the state-of-the-art multi-task SSL methods by up to 8.66% on the accuracy metric. The code of DyFSS is available at: https://github.com/q086/DyFSS.

Yu Wang, Junxian Mu, Pengfei Zhu et al.

Open set recognition (OSR) requires the model to classify samples that belong to closed sets while rejecting unknown samples during test. Currently, generative models often perform better than discriminative models in OSR, but recent studies show that generative models may be computationally infeasible or unstable on complex tasks. In this paper, we provide insights into OSR and find that learning supplementary representations can theoretically reduce the open space risk. Based on the analysis, we propose a new model, namely Multi-Expert Diverse Attention Fusion (MEDAF), that learns diverse representations in a discriminative way. MEDAF consists of multiple experts that are learned with an attention diversity regularization term to ensure the attention maps are mutually different. The logits learned by each expert are adaptively fused and used to identify the unknowns through the score function. We show that the differences in attention maps can lead to diverse representations so that the fused representations can well handle the open space. Extensive experiments are conducted on standard and OSR large-scale benchmarks. Results show that the proposed discriminative method can outperform existing generative models by up to 9.5% on AUROC and achieve new state-of-the-art performance with little computational cost. Our method can also seamlessly integrate existing classification models. Code is available at https://github.com/Vanixxz/MEDAF.

Liwei Luo, Shuaitengyuan Li, Dongwei Ren et al.

Recently, remarkable progress has been made in large-scale pre-trained model tuning, and inference efficiency is becoming more crucial for practical deployment. Early exiting in conjunction with multi-stage predictors, when cooperated with a parameter-efficient fine-tuning strategy, offers a straightforward way to achieve an inference-efficient model. However, a key challenge remains unresolved: How can early stages provide low-level fundamental features to deep stages while simultaneously supplying high-level discriminative features to early-stage predictors? To address this problem, we propose a Decoupled Multi-Predictor Optimization (DMPO) method to effectively decouple the low-level representative ability and high-level discriminative ability in early stages. First, in terms of architecture, we introduce a lightweight bypass module into multi-stage predictors for functional decomposition of shallow features from early stages, while a high-order statistics-based predictor is developed for early stages to effectively enhance their discriminative ability. To reasonably train our multi-predictor architecture, a decoupled optimization is proposed to allocate two-phase loss weights for multi-stage predictors during model tuning, where the initial training phase enables the model to prioritize the acquisition of discriminative ability of deep stages via emphasizing representative ability of early stages, and the latter training phase drives discriminative ability towards earlier stages as much as possible. As such, our DMPO can effectively decouple representative and discriminative abilities in early stages in terms of architecture design and model optimization. Experiments across various datasets and pre-trained backbones demonstrate that DMPO clearly outperforms its counterparts when reducing computational cost.

Wei Shang, Dongwei Ren, Wanying Zhang et al.

Local motion blur in digital images originates from the relative motion between dynamic objects and static imaging systems during exposure. Existing deblurring methods face significant challenges in addressing this problem due to their inefficient allocation of computational resources and inadequate handling of spatially varying blur patterns. To overcome these limitations, we first propose a trainable mask predictor that identifies blurred regions in the image. During training, we employ blur masks to exclude sharp regions. For inference optimization, we implement structural reparameterization by converting $3\times 3$ convolutions to computationally efficient $1\times 1$ convolutions, enabling pixel-level pruning of sharp areas to reduce computation. Second, we develop an intra-frame motion analyzer that translates relative pixel displacements into motion trajectories, establishing adaptive guidance for region-specific blur restoration. Our method is trained end-to-end using a combination of reconstruction loss, reblur loss, and mask loss guided by annotated blur masks. Extensive experiments demonstrate superior performance over state-of-the-art methods on both local and global blur datasets while reducing FLOPs by 49\% compared to SOTA models (e.g., LMD-ViT). The source code is available at https://github.com/shangwei5/M2AENet.

Wei Shang, Dongwei Ren, Wanying Zhang et al.

The primary challenge in accelerating image super-resolution lies in reducing computation while maintaining performance and adaptability. Motivated by the observation that high-frequency regions (e.g., edges and textures) are most critical for reconstruction, we propose a training-free adaptive masking module for acceleration that dynamically focuses computation on these challenging areas. Specifically, our method first extracts high-frequency components via Gaussian blur subtraction and adaptively generates binary masks using K-means clustering to identify regions requiring intensive processing. Our method can be easily integrated with both CNNs and Transformers. For CNN-based architectures, we replace standard $3 \times 3$ convolutions with an unfold operation followed by $1 \times 1$ convolutions, enabling pixel-wise sparse computation guided by the mask. For Transformer-based models, we partition the mask into non-overlapping windows and selectively process tokens based on their average values. During inference, unnecessary pixels or windows are pruned, significantly reducing computation. Moreover, our method supports dilation-based mask adjustment to control the processing scope without retraining, and is robust to unseen degradations (e.g., noise, compression). Extensive experiments on benchmarks demonstrate that our method reduces FLOPs by 24--43% for state-of-the-art models (e.g., CARN, SwinIR) while achieving comparable or better quantitative metrics. The source code is available at https://github.com/shangwei5/AMSR

Pengfei Zhu, Yang Sun, Bing Cao et al.

General image fusion aims at integrating important information from multi-source images. However, due to the significant cross-task gap, the respective fusion mechanism varies considerably in practice, resulting in limited performance across subtasks. To handle this problem, we propose a novel task-customized mixture of adapters (TC-MoA) for general image fusion, adaptively prompting various fusion tasks in a unified model. We borrow the insight from the mixture of experts (MoE), taking the experts as efficient tuning adapters to prompt a pre-trained foundation model. These adapters are shared across different tasks and constrained by mutual information regularization, ensuring compatibility with different tasks while complementarity for multi-source images. The task-specific routing networks customize these adapters to extract task-specific information from different sources with dynamic dominant intensity, performing adaptive visual feature prompt fusion. Notably, our TC-MoA controls the dominant intensity bias for different fusion tasks, successfully unifying multiple fusion tasks in a single model. Extensive experiments show that TC-MoA outperforms the competing approaches in learning commonalities while retaining compatibility for general image fusion (multi-modal, multi-exposure, and multi-focus), and also demonstrating striking controllability on more generalization experiments. The code is available at https://github.com/YangSun22/TC-MoA .

Congcong Li, Dawei Du, Libo Zhang et al.

Unsupervised domain adaptation is critical in various computer vision tasks, such as object detection, instance segmentation, and semantic segmentation, which aims to alleviate performance degradation caused by domain-shift. Most of previous methods rely on a single-mode distribution of source and target domains to align them with adversarial learning, leading to inferior results in various scenarios. To that end, in this paper, we design a new spatial attention pyramid network for unsupervised domain adaptation. Specifically, we first build the spatial pyramid representation to capture context information of objects at different scales. Guided by the task-specific information, we combine the dense global structure representation and local texture patterns at each spatial location effectively using the spatial attention mechanism. In this way, the network is enforced to focus on the discriminative regions with context information for domain adaption. We conduct extensive experiments on various challenging datasets for unsupervised domain adaptation on object detection, instance segmentation, and semantic segmentation, which demonstrates that our method performs favorably against the state-of-the-art methods by a large margin. Our source code is available at https://isrc.iscas.ac.cn/gitlab/research/domain-adaption.

Yiming Sun, Bing Cao, Pengfei Zhu et al.

Drone-based vehicle detection aims at finding the vehicle locations and categories in an aerial image. It empowers smart city traffic management and disaster rescue. Researchers have made mount of efforts in this area and achieved considerable progress. Nevertheless, it is still a challenge when the objects are hard to distinguish, especially in low light conditions. To tackle this problem, we construct a large-scale drone-based RGB-Infrared vehicle detection dataset, termed DroneVehicle. Our DroneVehicle collects 28, 439 RGB-Infrared image pairs, covering urban roads, residential areas, parking lots, and other scenarios from day to night. Due to the great gap between RGB and infrared images, cross-modal images provide both effective information and redundant information. To address this dilemma, we further propose an uncertainty-aware cross-modality vehicle detection (UA-CMDet) framework to extract complementary information from cross-modal images, which can significantly improve the detection performance in low light conditions. An uncertainty-aware module (UAM) is designed to quantify the uncertainty weights of each modality, which is calculated by the cross-modal Intersection over Union (IoU) and the RGB illumination value. Furthermore, we design an illumination-aware cross-modal non-maximum suppression algorithm to better integrate the modal-specific information in the inference phase. Extensive experiments on the DroneVehicle dataset demonstrate the flexibility and effectiveness of the proposed method for crossmodality vehicle detection. The dataset can be download from https://github.com/VisDrone/DroneVehicle.

Pengfei Zhu, Longyin Wen, Dawei Du et al.

Drones, or general UAVs, equipped with cameras have been fast deployed with a wide range of applications, including agriculture, aerial photography, and surveillance. Consequently, automatic understanding of visual data collected from drones becomes highly demanding, bringing computer vision and drones more and more closely. To promote and track the developments of object detection and tracking algorithms, we have organized three challenge workshops in conjunction with ECCV 2018, ICCV 2019 and ECCV 2020, attracting more than 100 teams around the world. We provide a large-scale drone captured dataset, VisDrone, which includes four tracks, i.e., (1) image object detection, (2) video object detection, (3) single object tracking, and (4) multi-object tracking. In this paper, we first present a thorough review of object detection and tracking datasets and benchmarks, and discuss the challenges of collecting large-scale drone-based object detection and tracking datasets with fully manual annotations. After that, we describe our VisDrone dataset, which is captured over various urban/suburban areas of 14 different cities across China from North to South. Being the largest such dataset ever published, VisDrone enables extensive evaluation and investigation of visual analysis algorithms for the drone platform. We provide a detailed analysis of the current state of the field of large-scale object detection and tracking on drones, and conclude the challenge as well as propose future directions. We expect the benchmark largely boost the research and development in video analysis on drone platforms. All the datasets and experimental results can be downloaded from https://github.com/VisDrone/VisDrone-Dataset.

Dongwei Ren, Wangmeng Zuo, Qinghua Hu et al.

Along with the deraining performance improvement of deep networks, their structures and learning become more and more complicated and diverse, making it difficult to analyze the contribution of various network modules when developing new deraining networks. To handle this issue, this paper provides a better and simpler baseline deraining network by considering network architecture, input and output, and loss functions. Specifically, by repeatedly unfolding a shallow ResNet, progressive ResNet (PRN) is proposed to take advantage of recursive computation. A recurrent layer is further introduced to exploit the dependencies of deep features across stages, forming our progressive recurrent network (PReNet). Furthermore, intra-stage recursive computation of ResNet can be adopted in PRN and PReNet to notably reduce network parameters with graceful degradation in deraining performance. For network input and output, we take both stage-wise result and original rainy image as input to each ResNet and finally output the prediction of {residual image}. As for loss functions, single MSE or negative SSIM losses are sufficient to train PRN and PReNet. Experiments show that PRN and PReNet perform favorably on both synthetic and real rainy images. Considering its simplicity, efficiency and effectiveness, our models are expected to serve as a suitable baseline in future deraining research. The source codes are available at https://github.com/csdwren/PReNet.

Yuwei Tang, Zhenyi Lin, Qilong Wang et al.

Recently, pre-trained vision-language models (e.g., CLIP) have shown great potential in few-shot learning and attracted a lot of research interest. Although efforts have been made to improve few-shot ability of CLIP, key factors on the effectiveness of existing methods have not been well studied, limiting further exploration of CLIP's potential in few-shot learning. In this paper, we first introduce a unified formulation to analyze CLIP-based few-shot learning methods from a perspective of logit bias, which encourages us to learn an effective logit bias for further improving performance of CLIP-based few-shot learning methods. To this end, we disassemble three key components involved in computation of logit bias (i.e., logit features, logit predictor, and logit fusion) and empirically analyze the effect on performance of few-shot classification. Based on analysis of key components, this paper proposes a novel AMU-Tuning method to learn effective logit bias for CLIP-based few-shot classification. Specifically, our AMU-Tuning predicts logit bias by exploiting the appropriate $\underline{\textbf{A}}$uxiliary features, which are fed into an efficient feature-initialized linear classifier with $\underline{\textbf{M}}$ulti-branch training. Finally, an $\underline{\textbf{U}}$ncertainty-based fusion is developed to incorporate logit bias into CLIP for few-shot classification. The experiments are conducted on several widely used benchmarks, and the results show AMU-Tuning clearly outperforms its counterparts while achieving state-of-the-art performance of CLIP-based few-shot learning without bells and whistles.

Bing Cao, Haiyu Yao, Pengfei Zhu et al.

Tiny object detection is one of the key challenges in the field of object detection. The performance of most generic detectors dramatically decreases in tiny object detection tasks. The main challenge lies in extracting effective features of tiny objects. Existing methods usually perform generation-based feature enhancement, which is seriously affected by spurious textures and artifacts, making it difficult to make the tiny-object-specific features visible and clear for detection. To address this issue, we propose a self-reconstructed tiny object detection (SR-TOD) framework. We for the first time introduce a self-reconstruction mechanism in the detection model, and discover the strong correlation between it and the tiny objects. Specifically, we impose a reconstruction head in-between the neck of a detector, constructing a difference map of the reconstructed image and the input, which shows high sensitivity to tiny objects. This inspires us to enhance the weak representations of tiny objects under the guidance of the difference maps. Thus, improving the visibility of tiny objects for the detectors. Building on this, we further develop a Difference Map Guided Feature Enhancement (DGFE) module to make the tiny feature representation more clear. In addition, we further propose a new multi-instance anti-UAV dataset, which is called DroneSwarms dataset and contains a large number of tiny drones with the smallest average size to date. Extensive experiments on the DroneSwarms dataset and other datasets demonstrate the effectiveness of the proposed method. The code and dataset will be publicly available.

Yan Fan, Yu Wang, Pengfei Zhu et al.

Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large number of labeled samples, making their real-life deployment challenging. In this work, we focus on semi-supervised continual learning (SSCL), where the model progressively learns from partially labeled data with unknown categories. We provide a comprehensive analysis of SSCL and demonstrate that unreliable distributions of unlabeled data lead to unstable training and refinement of the progressing stages. This problem severely impacts the performance of SSCL. To address the limitations, we propose a novel approach called Dynamic Sub-Graph Distillation (DSGD) for semi-supervised continual learning, which leverages both semantic and structural information to achieve more stable knowledge distillation on unlabeled data and exhibit robustness against distribution bias. Firstly, we formalize a general model of structural distillation and design a dynamic graph construction for the continual learning progress. Next, we define a structure distillation vector and design a dynamic sub-graph distillation algorithm, which enables end-to-end training and adaptability to scale up tasks. The entire proposed method is adaptable to various CL methods and supervision settings. Finally, experiments conducted on three datasets CIFAR10, CIFAR100, and ImageNet-100, with varying supervision ratios, demonstrate the effectiveness of our proposed approach in mitigating the catastrophic forgetting problem in semi-supervised continual learning scenarios.

Yuxin Yang, Pengfei Zhu, Mengshi Qi et al.

Human trajectory forecasting is a critical challenge in fields such as robotics and autonomous driving. Due to the inherent uncertainty of human actions and intentions in real-world scenarios, various unexpected occurrences may arise. To uncover latent motion patterns in human behavior, we introduce a novel memory-based method, named Motion Pattern Priors Memory Network. Our method involves constructing a memory bank derived from clustered prior knowledge of motion patterns observed in the training set trajectories. We introduce an addressing mechanism to retrieve the matched pattern and the potential target distributions for each prediction from the memory bank, which enables the identification and retrieval of natural motion patterns exhibited by agents, subsequently using the target priors memory token to guide the diffusion model to generate predictions. Extensive experiments validate the effectiveness of our approach, achieving state-of-the-art trajectory prediction accuracy. The code will be made publicly available.

Pengfei Zhu, Hongtao Yu, Kaihua Zhang et al.

Recently, template-based trackers have become the leading tracking algorithms with promising performance in terms of efficiency and accuracy. However, the correlation operation between query feature and the given template only exploits accurate target localization, leading to state estimation error especially when the target suffers from severe deformable variations. To address this issue, segmentation-based trackers have been proposed that employ per-pixel matching to improve the tracking performance of deformable objects effectively. However, most of existing trackers only refer to the target features in the initial frame, thereby lacking the discriminative capacity to handle challenging factors, e.g., similar distractors, background clutter, appearance change, etc. To this end, we propose a dynamic compact memory embedding to enhance the discrimination of the segmentation-based deformable visual tracking method. Specifically, we initialize a memory embedding with the target features in the first frame. During the tracking process, the current target features that have high correlation with existing memory are updated to the memory embedding online. To further improve the segmentation accuracy for deformable objects, we employ a point-to-global matching strategy to measure the correlation between the pixel-wise query features and the whole template, so as to capture more detailed deformation information. Extensive evaluations on six challenging tracking benchmarks including VOT2016, VOT2018, VOT2019, GOT-10K, TrackingNet, and LaSOT demonstrate the superiority of our method over recent remarkable trackers. Besides, our method outperforms the excellent segmentation-based trackers, i.e., D3S and SiamMask on DAVIS2017 benchmark.

Dawei Du, Longyin Wen, Pengfei Zhu et al.

Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint. However, there are few algorithms focusing on crowd counting on the drone-captured data due to the lack of comprehensive datasets. To this end, we collect a large-scale dataset and organize the Vision Meets Drone Crowd Counting Challenge (VisDrone-CC2020) in conjunction with the 16th European Conference on Computer Vision (ECCV 2020) to promote the developments in the related fields. The collected dataset is formed by $3,360$ images, including $2,460$ images for training, and $900$ images for testing. Specifically, we manually annotate persons with points in each video frame. There are $14$ algorithms from $15$ institutes submitted to the VisDrone-CC2020 Challenge. We provide a detailed analysis of the evaluation results and conclude the challenge. More information can be found at the website: \url{http://www.aiskyeye.com/}.

Longyin Wen, Dawei Du, Pengfei Zhu et al.

To promote the developments of object detection, tracking and counting algorithms in drone-captured videos, we construct a benchmark with a new drone-captured largescale dataset, named as DroneCrowd, formed by 112 video clips with 33,600 HD frames in various scenarios. Notably, we annotate 20,800 people trajectories with 4.8 million heads and several video-level attributes. Meanwhile, we design the Space-Time Neighbor-Aware Network (STNNet) as a strong baseline to solve object detection, tracking and counting jointly in dense crowds. STNNet is formed by the feature extraction module, followed by the density map estimation heads, and localization and association subnets. To exploit the context information of neighboring objects, we design the neighboring context loss to guide the association subnet training, which enforces consistent relative position of nearby objects in temporal domain. Extensive experiments on our DroneCrowd dataset demonstrate that STNNet performs favorably against the state-of-the-arts.

Junbing Li, Changqing Zhang, Pengfei Zhu et al.

Although significant progress achieved, multi-label classification is still challenging due to the complexity of correlations among different labels. Furthermore, modeling the relationships between input and some (dull) classes further increases the difficulty of accurately predicting all possible labels. In this work, we propose to select a small subset of labels as landmarks which are easy to predict according to input (predictable) and can well recover the other possible labels (representative). Different from existing methods which separate the landmark selection and landmark prediction in the 2-step manner, the proposed algorithm, termed Selecting Predictable Landmarks for Multi-Label Learning (SPL-MLL), jointly conducts landmark selection, landmark prediction, and label recovery in a unified framework, to ensure both the representativeness and predictableness for selected landmarks. We employ the Alternating Direction Method (ADM) to solve our problem. Empirical studies on real-world datasets show that our method achieves superior classification performance over other state-of-the-art methods.

Pengfei Zhu, Jiayu Zheng, Dawei Du et al.

Drone equipped with cameras can dynamically track the target in the air from a broader view compared with static cameras or moving sensors over the ground. However, it is still challenging to accurately track the target using a single drone due to several factors such as appearance variations and severe occlusions. In this paper, we collect a new Multi-Drone single Object Tracking (MDOT) dataset that consists of 92 groups of video clips with 113,918 high resolution frames taken by two drones and 63 groups of video clips with 145,875 high resolution frames taken by three drones. Besides, two evaluation metrics are specially designed for multi-drone single object tracking, i.e. automatic fusion score (AFS) and ideal fusion score (IFS). Moreover, an agent sharing network (ASNet) is proposed by self-supervised template sharing and view-aware fusion of the target from multiple drones, which can improve the tracking accuracy significantly compared with single drone tracking. Extensive experiments on MDOT show that our ASNet significantly outperforms recent state-of-the-art trackers.

Longyin Wen, Dawei Du, Pengfei Zhu et al.

This paper proposes a space-time multi-scale attention network (STANet) to solve density map estimation, localization and tracking in dense crowds of video clips captured by drones with arbitrary crowd density, perspective, and flight altitude. Our STANet method aggregates multi-scale feature maps in sequential frames to exploit the temporal coherency, and then predict the density maps, localize the targets, and associate them in crowds simultaneously. A coarse-to-fine process is designed to gradually apply the attention module on the aggregated multi-scale feature maps to enforce the network to exploit the discriminative space-time features for better performance. The whole network is trained in an end-to-end manner with the multi-task loss, formed by three terms, i.e., the density map loss, localization loss and association loss. The non-maximal suppression followed by the min-cost flow framework is used to generate the trajectories of targets' in scenarios. Since existing crowd counting datasets merely focus on crowd counting in static cameras rather than density map estimation, counting and tracking in crowds on drones, we have collected a new large-scale drone-based dataset, DroneCrowd, formed by 112 video clips with 33,600 high resolution frames (i.e., 1920x1080) captured in 70 different scenarios. With intensive amount of effort, our dataset provides 20,800 people trajectories with 4.8 million head annotations and several video-level attributes in sequences. Extensive experiments are conducted on two challenging public datasets, i.e., Shanghaitech and UCF-QNRF, and our DroneCrowd, to demonstrate that STANet achieves favorable performance against the state-of-the-arts. The datasets and codes can be found at https://github.com/VisDrone.

Qilong Wang, Banggu Wu, Pengfei Zhu et al.

Recently, channel attention mechanism has demonstrated to offer great potential in improving the performance of deep convolutional neural networks (CNNs). However, most existing methods dedicate to developing more sophisticated attention modules for achieving better performance, which inevitably increase model complexity. To overcome the paradox of performance and complexity trade-off, this paper proposes an Efficient Channel Attention (ECA) module, which only involves a handful of parameters while bringing clear performance gain. By dissecting the channel attention module in SENet, we empirically show avoiding dimensionality reduction is important for learning channel attention, and appropriate cross-channel interaction can preserve performance while significantly decreasing model complexity. Therefore, we propose a local cross-channel interaction strategy without dimensionality reduction, which can be efficiently implemented via $1D$ convolution. Furthermore, we develop a method to adaptively select kernel size of $1D$ convolution, determining coverage of local cross-channel interaction. The proposed ECA module is efficient yet effective, e.g., the parameters and computations of our modules against backbone of ResNet50 are 80 vs. 24.37M and 4.7e-4 GFLOPs vs. 3.86 GFLOPs, respectively, and the performance boost is more than 2% in terms of Top-1 accuracy. We extensively evaluate our ECA module on image classification, object detection and instance segmentation with backbones of ResNets and MobileNetV2. The experimental results show our module is more efficient while performing favorably against its counterparts.

Pengfei Zhu, Xinjie Yao, Yu Wang et al.

Multi-view subspace clustering aims to discover the inherent structure of data by fusing multiple views of complementary information. Most existing methods first extract multiple types of handcrafted features and then learn a joint affinity matrix for clustering. The disadvantage of this approach lies in two aspects: 1) multi-view relations are not embedded into feature learning, and 2) the end-to-end learning manner of deep learning is not suitable for multi-view clustering. Even when deep features have been extracted, it is a nontrivial problem to choose a proper backbone for clustering on different datasets. To address these issues, we propose the Multi-view Deep Subspace Clustering Networks (MvDSCN), which learns a multi-view self-representation matrix in an end-to-end manner. The MvDSCN consists of two sub-networks, \ie, a diversity network (Dnet) and a universality network (Unet). A latent space is built using deep convolutional autoencoders, and a self-representation matrix is learned in the latent space using a fully connected layer. Dnet learns view-specific self-representation matrices, whereas Unet learns a common self-representation matrix for all views. To exploit the complementarity of multi-view representations, the Hilbert--Schmidt independence criterion (HSIC) is introduced as a diversity regularizer that captures the nonlinear, high-order inter-view relations. Because different views share the same label space, the self-representation matrices of each view are aligned to the common one by universality regularization. The MvDSCN also unifies multiple backbones to boost clustering performance and avoid the need for model selection. Experiments demonstrate the superiority of the MvDSCN.

Andrey Ignatov, Radu Timofte, Thang Van Vu et al.

This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones. The challenge consisted of two tracks. In the first one, participants were solving the classical image super-resolution problem with a bicubic downscaling factor of 4. The second track was aimed at real-world photo enhancement, and the goal was to map low-quality photos from the iPhone 3GS device to the same photos captured with a DSLR camera. The target metric used in this challenge combined the runtime, PSNR scores and solutions' perceptual results measured in the user study. To ensure the efficiency of the submitted models, we additionally measured their runtime and memory requirements on Android smartphones. The proposed solutions significantly improved baseline results defining the state-of-the-art for image enhancement on smartphones.

Pengfei Zhu, Longyin Wen, Xiao Bian et al.

In this paper we present a large-scale visual object detection and tracking benchmark, named VisDrone2018, aiming at advancing visual understanding tasks on the drone platform. The images and video sequences in the benchmark were captured over various urban/suburban areas of 14 different cities across China from north to south. Specifically, VisDrone2018 consists of 263 video clips and 10,209 images (no overlap with video clips) with rich annotations, including object bounding boxes, object categories, occlusion, truncation ratios, etc. With intensive amount of effort, our benchmark has more than 2.5 million annotated instances in 179,264 images/video frames. Being the largest such dataset ever published, the benchmark enables extensive evaluation and investigation of visual analysis algorithms on the drone platform. In particular, we design four popular tasks with the benchmark, including object detection in images, object detection in videos, single object tracking, and multi-object tracking. All these tasks are extremely challenging in the proposed dataset due to factors such as occlusion, large scale and pose variation, and fast motion. We hope the benchmark largely boost the research and development in visual analysis on drone platforms.

Pengfei Zhu, Xin Li, Pascal Poupart et al.

Deep Reinforcement Learning (RL) recently emerged as one of the most competitive approaches for learning in sequential decision making problems with fully observable environments, e.g., computer Go. However, very little work has been done in deep RL to handle partially observable environments. We propose a new architecture called Action-specific Deep Recurrent Q-Network (ADRQN) to enhance learning performance in partially observable domains. Actions are encoded by a fully connected layer and coupled with a convolutional observation to form an action-observation pair. The time series of action-observation pairs are then integrated by an LSTM layer that learns latent states based on which a fully connected layer computes Q-values as in conventional Deep Q-Networks (DQNs). We demonstrate the effectiveness of our new architecture in several partially observable domains, including flickering Atari games.