Xin Zhao

Fei He, Naiyu Gao, Jian Jia et al.

Video object detection has been an important yet challenging topic in computer vision. Traditional methods mainly focus on designing the image-level or box-level feature propagation strategies to exploit temporal information. This paper argues that with a more effective and efficient feature propagation framework, video object detectors can gain improvement in terms of both accuracy and speed. For this purpose, this paper studies object-level feature propagation, and proposes an object query propagation (QueryProp) framework for high-performance video object detection. The proposed QueryProp contains two propagation strategies: 1) query propagation is performed from sparse key frames to dense non-key frames to reduce the redundant computation on non-key frames; 2) query propagation is performed from previous key frames to the current key frame to improve feature representation by temporal context modeling. To further facilitate query propagation, an adaptive propagation gate is designed to achieve flexible key frame selection. We conduct extensive experiments on the ImageNet VID dataset. QueryProp achieves comparable accuracy with state-of-the-art methods and strikes a decent accuracy/speed trade-off. Code is available at https://github.com/hf1995/QueryProp.

Jun Zhao, Wenyu Zhan, Xin Zhao et al.

Semantic matching is a mainstream paradigm of zero-shot relation extraction, which matches a given input with a corresponding label description. The entities in the input should exactly match their hypernyms in the description, while the irrelevant contexts should be ignored when matching. However, general matching methods lack explicit modeling of the above matching pattern. In this work, we propose a fine-grained semantic matching method tailored for zero-shot relation extraction. Following the above matching pattern, we decompose the sentence-level similarity score into entity and context matching scores. Due to the lack of explicit annotations of the redundant components, we design a feature distillation module to adaptively identify the relation-irrelevant features and reduce their negative impact on context matching. Experimental results show that our method achieves higher matching $F_1$ score and has an inference speed 10 times faster, when compared with the state-of-the-art methods.

Shiyue Cao, Yueqin Yin, Lianghua Huang et al.

Vector-quantized image modeling has shown great potential in synthesizing high-quality images. However, generating high-resolution images remains a challenging task due to the quadratic computational overhead of the self-attention process. In this study, we seek to explore a more efficient two-stage framework for high-resolution image generation with improvements in the following three aspects. (1) Based on the observation that the first quantization stage has solid local property, we employ a local attention-based quantization model instead of the global attention mechanism used in previous methods, leading to better efficiency and reconstruction quality. (2) We emphasize the importance of multi-grained feature interaction during image generation and introduce an efficient attention mechanism that combines global attention (long-range semantic consistency within the whole image) and local attention (fined-grained details). This approach results in faster generation speed, higher generation fidelity, and improved resolution. (3) We propose a new generation pipeline incorporating autoencoding training and autoregressive generation strategy, demonstrating a better paradigm for image synthesis. Extensive experiments demonstrate the superiority of our approach in high-quality and high-resolution image reconstruction and generation.

Lin Wang, Xiufen Ye, Donghao Zhang et al.

Usually, lesions are not isolated but are associated with the surrounding tissues. For example, the growth of a tumour can depend on or infiltrate into the surrounding tissues. Due to the pathological nature of the lesions, it is challenging to distinguish their boundaries in medical imaging. However, these uncertain regions may contain diagnostic information. Therefore, the simple binarization of lesions by traditional binary segmentation can result in the loss of diagnostic information. In this work, we introduce the image matting into the 3D scenes and use the alpha matte, i.e., a soft mask, to describe lesions in a 3D medical image. The traditional soft mask acted as a training trick to compensate for the easily mislabelled or under-labelled ambiguous regions. In contrast, 3D matting uses soft segmentation to characterize the uncertain regions more finely, which means that it retains more structural information for subsequent diagnosis and treatment. The current study of image matting methods in 3D is limited. To address this issue, we conduct a comprehensive study of 3D matting, including both traditional and deep-learning-based methods. We adapt four state-of-the-art 2D image matting algorithms to 3D scenes and further customize the methods for CT images to calibrate the alpha matte with the radiodensity. Moreover, we propose the first end-to-end deep 3D matting network and implement a solid 3D medical image matting benchmark. Its efficient counterparts are also proposed to achieve a good performance-computation balance. Furthermore, there is no high-quality annotated dataset related to 3D matting, slowing down the development of data-driven deep-learning-based methods. To address this issue, we construct the first 3D medical matting dataset. The validity of the dataset was verified through clinicians' assessments and downstream experiments.

Lianghua Huang, Xin Zhao, Kaiqi Huang

A key capability of a long-term tracker is to search for targets in very large areas (typically the entire image) to handle possible target absences or tracking failures. However, currently there is a lack of such a strong baseline for global instance search. In this work, we aim to bridge this gap. Specifically, we propose GlobalTrack, a pure global instance search based tracker that makes no assumption on the temporal consistency of the target's positions and scales. GlobalTrack is developed based on two-stage object detectors, and it is able to perform full-image and multi-scale search of arbitrary instances with only a single query as the guide. We further propose a cross-query loss to improve the robustness of our approach against distractors. With no online learning, no punishment on position or scale changes, no scale smoothing and no trajectory refinement, our pure global instance search based tracker achieves comparable, sometimes much better performance on four large-scale tracking benchmarks (i.e., 52.1% AUC on LaSOT, 63.8% success rate on TLP, 60.3% MaxGM on OxUvA and 75.4% normalized precision on TrackingNet), compared to state-of-the-art approaches that typically require complex post-processing. More importantly, our tracker runs without cumulative errors, i.e., any type of temporary tracking failures will not affect its performance on future frames, making it ideal for long-term tracking. We hope this work will be a strong baseline for long-term tracking and will stimulate future works in this area. Code is available at https://github.com/huanglianghua/GlobalTrack.

Honghao Chen, Xiangxiang Chu, Yongjian Ren et al.

Recently, some large kernel convnets strike back with appealing performance and efficiency. However, given the square complexity of convolution, scaling up kernels can bring about an enormous amount of parameters and the proliferated parameters can induce severe optimization problem. Due to these issues, current CNNs compromise to scale up to 51x51 in the form of stripe convolution (i.e., 51x5 + 5x51) and start to saturate as the kernel size continues growing. In this paper, we delve into addressing these vital issues and explore whether we can continue scaling up kernels for more performance gains. Inspired by human vision, we propose a human-like peripheral convolution that efficiently reduces over 90% parameter count of dense grid convolution through parameter sharing, and manage to scale up kernel size to extremely large. Our peripheral convolution behaves highly similar to human, reducing the complexity of convolution from O(K^2) to O(logK) without backfiring performance. Built on this, we propose Parameter-efficient Large Kernel Network (PeLK). Our PeLK outperforms modern vision Transformers and ConvNet architectures like Swin, ConvNeXt, RepLKNet and SLaK on various vision tasks including ImageNet classification, semantic segmentation on ADE20K and object detection on MS COCO. For the first time, we successfully scale up the kernel size of CNNs to an unprecedented 101x101 and demonstrate consistent improvements.

Xin Zhao, Shiyu Hu, Yipei Wang et al.

Single object tracking (SOT) is a fundamental problem in computer vision, with a wide range of applications, including autonomous driving, augmented reality, and robot navigation. The robustness of SOT faces two main challenges: tiny target and fast motion. These challenges are especially manifested in videos captured by unmanned aerial vehicles (UAV), where the target is usually far away from the camera and often with significant motion relative to the camera. To evaluate the robustness of SOT methods, we propose BioDrone -- the first bionic drone-based visual benchmark for SOT. Unlike existing UAV datasets, BioDrone features videos captured from a flapping-wing UAV system with a major camera shake due to its aerodynamics. BioDrone hence highlights the tracking of tiny targets with drastic changes between consecutive frames, providing a new robust vision benchmark for SOT. To date, BioDrone offers the largest UAV-based SOT benchmark with high-quality fine-grained manual annotations and automatically generates frame-level labels, designed for robust vision analyses. Leveraging our proposed BioDrone, we conduct a systematic evaluation of existing SOT methods, comparing the performance of 20 representative models and studying novel means of optimizing a SOTA method (KeepTrack KeepTrack) for robust SOT. Our evaluation leads to new baselines and insights for robust SOT. Moving forward, we hope that BioDrone will not only serve as a high-quality benchmark for robust SOT, but also invite future research into robust computer vision. The database, toolkits, evaluation server, and baseline results are available at http://biodrone.aitestunion.com.

Lie Ju, Zhen Yu, Lin Wang et al.

In the real world, medical datasets often exhibit a long-tailed data distribution (i.e., a few classes occupy the majority of the data, while most classes have only a limited number of samples), which results in a challenging long-tailed learning scenario. Some recently published datasets in ophthalmology AI consist of more than 40 kinds of retinal diseases with complex abnormalities and variable morbidity. Nevertheless, more than 30 conditions are rarely seen in global patient cohorts. From a modeling perspective, most deep learning models trained on these datasets may lack the ability to generalize to rare diseases where only a few available samples are presented for training. In addition, there may be more than one disease for the presence of the retina, resulting in a challenging label co-occurrence scenario, also known as \textit{multi-label}, which can cause problems when some re-sampling strategies are applied during training. To address the above two major challenges, this paper presents a novel method that enables the deep neural network to learn from a long-tailed fundus database for various retinal disease recognition. Firstly, we exploit the prior knowledge in ophthalmology to improve the feature representation using a hierarchy-aware pre-training. Secondly, we adopt an instance-wise class-balanced sampling strategy to address the label co-occurrence issue under the long-tailed medical dataset scenario. Thirdly, we introduce a novel hybrid knowledge distillation to train a less biased representation and classifier. We conducted extensive experiments on four databases, including two public datasets and two in-house databases with more than one million fundus images. The experimental results demonstrate the superiority of our proposed methods with recognition accuracy outperforming the state-of-the-art competitors, especially for these rare diseases.

Wei Feng, Lie Ju, Lin Wang et al.

Retinal vessel segmentation plays a key role in computer-aided screening, diagnosis, and treatment of various cardiovascular and ophthalmic diseases. Recently, deep learning-based retinal vessel segmentation algorithms have achieved remarkable performance. However, due to the domain shift problem, the performance of these algorithms often degrades when they are applied to new data that is different from the training data. Manually labeling new data for each test domain is often a time-consuming and laborious task. In this work, we explore unsupervised domain adaptation in retinal vessel segmentation by using entropy-based adversarial learning and transfer normalization layer to train a segmentation network, which generalizes well across domains and requires no annotation of the target domain. Specifically, first, an entropy-based adversarial learning strategy is developed to reduce the distribution discrepancy between the source and target domains while also achieving the objective of entropy minimization on the target domain. In addition, a new transfer normalization layer is proposed to further boost the transferability of the deep network. It normalizes the features of each domain separately to compensate for the domain distribution gap. Besides, it also adaptively selects those feature channels that are more transferable between domains, thus further enhancing the generalization performance of the network. We conducted extensive experiments on three regular fundus image datasets and an ultra-widefield fundus image dataset, and the results show that our approach yields significant performance gains compared to other state-of-the-art methods.

Lin Wang, Lie Ju, Xin Wang et al.

It is difficult to accurately label ambiguous and complex shaped targets manually by binary masks. The weakness of binary mask under-expression is highlighted in medical image segmentation, where blurring is prevalent. In the case of multiple annotations, reaching a consensus for clinicians by binary masks is more challenging. Moreover, these uncertain areas are related to the lesions' structure and may contain anatomical information beneficial to diagnosis. However, current studies on uncertainty mainly focus on the uncertainty in model training and data labels. None of them investigate the influence of the ambiguous nature of the lesion itself.Inspired by image matting, this paper introduces alpha matte as a soft mask to represent uncertain areas in medical scenes and accordingly puts forward a new uncertainty quantification method to fill the gap of uncertainty research for lesion structure. In this work, we introduce a new architecture to generate binary masks and alpha mattes in a multitasking framework, which outperforms all state-of-the-art matting algorithms compared. The proposed uncertainty map is able to highlight the ambiguous regions and a novel multitasking loss weighting strategy we presented can improve performance further and demonstrate their concrete benefits. To fully-evaluate the effectiveness of our proposed method, we first labelled three medical datasets with alpha matte to address the shortage of available matting datasets in medical scenes and prove the alpha matte to be a more efficient labeling method than a binary mask from both qualitative and quantitative aspects.

Lie Ju, Xin Wang, Lin Wang et al.

In the real world, medical datasets often exhibit a long-tailed data distribution (i.e., a few classes occupy most of the data, while most classes have rarely few samples), which results in a challenging imbalance learning scenario. For example, there are estimated more than 40 different kinds of retinal diseases with variable morbidity, however with more than 30+ conditions are very rare from the global patient cohorts, which results in a typical long-tailed learning problem for deep learning-based screening models. In this study, we propose class subset learning by dividing the long-tailed data into multiple class subsets according to prior knowledge, such as regions and phenotype information. It enforces the model to focus on learning the subset-specific knowledge. More specifically, there are some relational classes that reside in the fixed retinal regions, or some common pathological features are observed in both the majority and minority conditions. With those subsets learnt teacher models, then we are able to distill the multiple teacher models into a unified model with weighted knowledge distillation loss. The proposed framework proved to be effective for the long-tailed retinal diseases recognition task. The experimental results on two different datasets demonstrate that our method is flexible and can be easily plugged into many other state-of-the-art techniques with significant improvements.

Lie Ju, Xin Wang, Lin Wang et al.

Deep neural networks are known to be data-driven and label noise can have a marked impact on model performance. Recent studies have shown great robustness to classic image recognition even under a high noisy rate. In medical applications, learning from datasets with label noise is more challenging since medical imaging datasets tend to have asymmetric (class-dependent) noise and suffer from high observer variability. In this paper, we systematically discuss and define the two common types of label noise in medical images - disagreement label noise from inconsistency expert opinions and single-target label noise from wrong diagnosis record. We then propose an uncertainty estimation-based framework to handle these two label noise amid the medical image classification task. We design a dual-uncertainty estimation approach to measure the disagreement label noise and single-target label noise via Direct Uncertainty Prediction and Monte-Carlo-Dropout. A boosting-based curriculum training procedure is later introduced for robust learning. We demonstrate the effectiveness of our method by conducting extensive experiments on three different diseases: skin lesions, prostate cancer, and retinal diseases. We also release a large re-engineered database that consists of annotations from more than ten ophthalmologists with an unbiased golden standard dataset for evaluation and benchmarking.

Lie Ju, Xin Wang, Xin Zhao et al.

The need for comprehensive and automated screening methods for retinal image classification has long been recognized. Well-qualified doctors annotated images are very expensive and only a limited amount of data is available for various retinal diseases such as age-related macular degeneration (AMD) and diabetic retinopathy (DR). Some studies show that AMD and DR share some common features like hemorrhagic points and exudation but most classification algorithms only train those disease models independently. Inspired by knowledge distillation where additional monitoring signals from various sources is beneficial to train a robust model with much fewer data. We propose a method called synergic adversarial label learning (SALL) which leverages relevant retinal disease labels in both semantic and feature space as additional signals and train the model in a collaborative manner. Our experiments on DR and AMD fundus image classification task demonstrate that the proposed method can significantly improve the accuracy of the model for grading diseases. In addition, we conduct additional experiments to show the effectiveness of SALL from the aspects of reliability and interpretability in the context of medical imaging application.

Zhe Liu, Xin Zhao, Tengteng Huang et al.

In this paper, we focus on exploring the robustness of the 3D object detection in point clouds, which has been rarely discussed in existing approaches. We observe two crucial phenomena: 1) the detection accuracy of the hard objects, e.g., Pedestrians, is unsatisfactory, 2) when adding additional noise points, the performance of existing approaches decreases rapidly. To alleviate these problems, a novel TANet is introduced in this paper, which mainly contains a Triple Attention (TA) module, and a Coarse-to-Fine Regression (CFR) module. By considering the channel-wise, point-wise and voxel-wise attention jointly, the TA module enhances the crucial information of the target while suppresses the unstable cloud points. Besides, the novel stacked TA further exploits the multi-level feature attention. In addition, the CFR module boosts the accuracy of localization without excessive computation cost. Experimental results on the validation set of KITTI dataset demonstrate that, in the challenging noisy cases, i.e., adding additional random noisy points around each object,the presented approach goes far beyond state-of-the-art approaches. Furthermore, for the 3D object detection task of the KITTI benchmark, our approach ranks the first place on Pedestrian class, by using the point clouds as the only input. The running speed is around 29 frames per second.

Naiyu Gao, Yanhu Shan, Yupei Wang et al.

Recently, proposal-free instance segmentation has received increasing attention due to its concise and efficient pipeline. Generally, proposal-free methods generate instance-agnostic semantic segmentation labels and instance-aware features to group pixels into different object instances. However, previous methods mostly employ separate modules for these two sub-tasks and require multiple passes for inference. We argue that treating these two sub-tasks separately is suboptimal. In fact, employing multiple separate modules significantly reduces the potential for application. The mutual benefits between the two complementary sub-tasks are also unexplored. To this end, this work proposes a single-shot proposal-free instance segmentation method that requires only one single pass for prediction. Our method is based on a pixel-pair affinity pyramid, which computes the probability that two pixels belong to the same instance in a hierarchical manner. The affinity pyramid can also be jointly learned with the semantic class labeling and achieve mutual benefits. Moreover, incorporating with the learned affinity pyramid, a novel cascaded graph partition module is presented to sequentially generate instances from coarse to fine. Unlike previous time-consuming graph partition methods, this module achieves $5\times$ speedup and 9% relative improvement on Average-Precision (AP). Our approach achieves state-of-the-art results on the challenging Cityscapes dataset.

Lianghua Huang, Xin Zhao, Kaiqi Huang

We introduce here a large tracking database that offers an unprecedentedly wide coverage of common moving objects in the wild, called GOT-10k. Specifically, GOT-10k is built upon the backbone of WordNet structure and it populates the majority of over 560 classes of moving objects and 87 motion patterns, magnitudes wider than the most recent similar-scale counterparts. The contributions of this paper are summarized in the following: (1) GOT-10k offers over 10,000 video segments with more than 1.5 million manually labeled bounding boxes, enabling unified training and stable evaluation of deep trackers. (2) GOT-10k is by far the first video trajectory dataset that uses the semantic hierarchy of WordNet to guide class population. (3) For the first time, GOT-10k introduces the one-shot protocol for tracker evaluation, where the training and test classes are zero-overlapped. The protocol avoids biased evaluation results towards familiar objects and it promotes generalization in tracker development. (4) We conduct extensive tracking experiments with 39 typical tracking algorithms on GOT-10k and analyze their results in this paper. (5) Finally, we develop a comprehensive platform for the tracking community that offers full-featured evaluation toolkits, an online evaluation server, and a responsive leaderboard. The annotations of GOT-10k's test data are kept private to avoid tuning parameters on it. The database, toolkits, evaluation server and baseline results are available at http://got-10k.aitestunion.com.

Xin Zhao, Arie Kaufman

Radiological imaging of prostate is becoming more popular among researchers and clinicians in searching for diseases, primarily cancer. Scans might be acquired at different times, with patient movement between scans, or with different equipment, resulting in multiple datasets that need to be registered. For this issue, we introduce a registration method using anatomical feature-guided mutual information. Prostate scans of the same patient taken in three different orientations are first aligned for the accurate detection of anatomical features in 3D. Then, our pipeline allows for multiple modalities registration through the use of anatomical features, such as the interior urethra of prostate and gland utricle, in a bijective way. The novelty of this approach is the application of anatomical features as the pre-specified corresponding landmarks for prostate registration. We evaluate the registration results through both artificial and clinical datasets. Registration accuracy is evaluated by performing statistical analysis of local intensity differences or spatial differences of anatomical landmarks between various MR datasets. Evaluation results demonstrate that our method statistics-significantly improves the quality of registration. Although this strategy is tested for MRI-guided brachytherapy, the preliminary results from these experiments suggest that it can be also applied to other settings such as transrectal ultrasound-guided or CT-guided therapy, where the integration of preoperative MRI may have a significant impact upon treatment planning and guidance.