\begin{abstract} Learning-based methods suffer from a deficiency of clean annotations, especially in biomedical segmentation. Although many semi-supervised methods have been proposed to provide extra training data, automatically generated labels are usually too noisy to retrain models effectively. In this paper, we propose a Two-Stream Mutual Attention Network (TSMAN) that weakens the influence of back-propagated gradients caused by incorrect labels, thereby rendering the network robust to unclean data. The proposed TSMAN consists of two sub-networks that are connected by three types of attention models in different layers. The target of each attention model is to indicate potentially incorrect gradients in a certain layer for both sub-networks by analyzing their inferred features using the same input. In order to achieve this purpose, the attention models are designed based on the propagation analysis of noisy gradients at different layers. This allows the attention models to effectively discover incorrect labels and weaken their influence during the parameter updating process. By exchanging multi-level features within the two-stream architecture, the effects of noisy labels in each sub-network are reduced by decreasing the updating gradients. Furthermore, a hierarchical distillation is developed to provide more reliable pseudo labels for unlabelded data, which further boosts the performance of our retrained TSMAN. The experiments using both the HVSMR 2016 and BRATS 2015 benchmarks demonstrate that our semi-supervised learning framework surpasses the state-of-the-art fully-supervised results.
University of Notre Dame（圣母大学）；Allen Institute for Cell Science（艾伦细胞科学研究所）
The Encoder-Decoder architecture is a main stream deep learning model for biomedical image segmentation. The encoder fully compresses the input and generates encoded features, and the decoder then produces dense predictions using encoded features. However, decoders are still under-explored in such architectures. In this paper, we comprehensively study the state-of-the-art Encoder-Decoder architectures, and propose a new universal decoder, called cascade decoder, to improve semantic segmentation accuracy. Our cascade decoder can be embedded into existing networks and trained altogether in an en…
Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization
College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；Zhejiang Lab（之江实验室）；School of Cyber Science and Technology, Zhejiang University（浙江大学网络空间安全学院）；Public Computer Education and Research Center, Jilin University（吉林大学公共计算机教育与研究中心）；Black Sesame Technologies（黑芝麻科技）
Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an alternative strategy where multiple simple student networks benefit from sharing knowledge, even in the absence of a powerful but static teacher network. Motivated by these findings, we propose a single-teacher, multi-student framework that leverages both KD and ML to achieve better performance. Furthermore, an online distillation strategy is utilized to train the te…
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Dynamic Vision Sensor (DVS) can asynchronously output the events reflecting apparent motion of objects with microsecond resolution, and shows great application potential in monitoring and other fields. However, the output event stream of existing DVS inevitably contains background activity noise (BA noise) due to dark current and junction leakage current, which will affect the temporal correlation of objects, resulting in deteriorated motion estimation performance. Particularly, the existing filter-based denoising methods cannot be directly applied to suppress the noise in event stream, since …
Northwestern Polytechnical University（西北工业大学）；University of Adelaide（阿德莱德大学）
The Classification of medical images and illustrations in the literature aims to label a medical image according to the modality it was produced or label an illustration according to its production attributes. It is an essential and challenging research hotspot in the area of automated literature review, retrieval and mining. The significant intra-class variation and inter-class similarity caused by the diverse imaging modalities and various illustration types brings a great deal of difficulties to the problem. In this paper, we propose a synergic deep learning (SDL) model to address this issu…
People's looking at each other or mutual gaze is ubiquitous in our daily interactions, and detecting mutual gaze is of great significance for understanding human social scenes. Current mutual gaze detection methods focus on two-stage methods, whose inference speed is limited by the two-stage pipeline and the performance in the second stage is affected by the first one. In this paper, we propose a novel one-stage mutual gaze detection framework called Mutual Gaze TRansformer or MGTR to perform mutual gaze detection in an end-to-end manner. By designing mutual gaze instance triples, MGTR can det…
University of Texas at Dallas（德克萨斯大学达拉斯分校）；Adobe Research（奥多比研究院）
Deep neural networks based object detectors have shown great success in a variety of domains like autonomous vehicles, biomedical imaging, etc. It is known that their success depends on a large amount of data from the domain of interest. While deep models often perform well in terms of overall accuracy, they often struggle in performance on rare yet critical data slices. For example, data slices like "motorcycle at night" or "bicycle at night" are often rare but very critical slices for self-driving applications and false negatives on such rare slices could result in ill-fated failures and acc…
Learning-based hashing methods are widely used for nearest neighbor retrieval, and recently, online hashing methods have demonstrated good performance-complexity trade-offs by learning hash functions from streaming data. In this paper, we first address a key challenge for online hashing: the binary codes for indexed data must be recomputed to keep pace with updates to the hash functions. We propose an efficient quality measure for hash functions, based on an information-theoretic quantity, mutual information, and use it successfully as a criterion to eliminate unnecessary hash table updates. N…
Institute of Computer Science and Technology, Peking University（北京大学计算机科学技术研究所）
Video classification is highly important with wide applications, such as video search and intelligent surveillance. Video naturally consists of static and motion information, which can be represented by frame and optical flow. Recently, researchers generally adopt the deep networks to capture the static and motion information \textbf{\emph{separately}}, which mainly has two limitations: (1) Ignoring the coexistence relationship between spatial and temporal attention, while they should be jointly modelled as the spatial and temporal evolutions of video, thus discriminative video features can be…
Alignment of contrast and non-contrast-enhanced imaging is essential for the quantification of changes in several biomedical applications. In particular, the extraction of cartilage shape from contrast-enhanced Computed Tomography (CT) of tibiae requires accurate alignment of the bone, currently performed manually. Existing deep learning-based methods for alignment require a common template or are limited in rotation range. Therefore, we present a novel network, D-net, to estimate arbitrary rotation and translation between 3D CT scans that additionally does not require a prior standard templat…
Referring video segmentation aims to segment the corresponding video object described by the language expression. To address this task, we first design a two-stream encoder to extract CNN-based visual features and transformer-based linguistic features hierarchically, and a vision-language mutual guidance (VLMG) module is inserted into the encoder multiple times to promote the hierarchical and progressive fusion of multi-modal features. Compared with the existing multi-modal fusion methods, this two-stream encoder takes into account the multi-granularity linguistic context, and realizes the dee…
Nanyang Technological University（南洋理工大学）；ByteDance AI Lab（字节跳动人工智能实验室）；ByteDance（字节跳动）
In this work, we aim to address the challenging task of open set recognition (OSR). Many recent OSR methods rely on auto-encoders to extract class-specific features by a reconstruction strategy, requiring the network to restore the input image on pixel-level. This strategy is commonly over-demanding for OSR since class-specific features are generally contained in target objects, not in all pixels. To address this shortcoming, here we discard the pixel-level reconstruction strategy and pay more attention to improving the effectiveness of class-specific feature extraction. We propose a mutual in…
École de technologie supérieure（高等技术学院）；Genetec Inc.（杰尼特克公司）；Sportlogiq Inc.（斯波特洛吉克公司）
Person Re-Identification (ReID) is a challenging problem in many video analytics and surveillance applications, where a person's identity must be associated across a distributed non-overlapping network of cameras. Video-based person ReID has recently gained much interest because it allows capturing discriminant spatio-temporal information from video clips that is unavailable for image-based ReID. Despite recent advances, deep learning (DL) models for video ReID often fail to leverage this information to improve the robustness of feature representations. In this paper, the motion pattern of a p…
Video anomaly detection aims to find the events in a video that do not conform to the expected behavior. The prevalent methods mainly detect anomalies by snippet reconstruction or future frame prediction error. However, the error is highly dependent on the local context of the current snippet and lacks the understanding of normality. To address this issue, we propose to detect anomalous events not only by the local context, but also according to the consistency between the testing event and the knowledge about normality from the training data. Concretely, we propose a novel two-stream framewor…
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Northwestern Polytechnical University（西北工业大学）；Inception Institute of Artificial Intelligence（因塞普申人工智能研究院）
How to effectively fuse cross-modal information is the key problem for RGB-D salient object detection. Early fusion and the result fusion schemes fuse RGB and depth information at the input and output stages, respectively, hence incur the problem of distribution gap or information loss. Many models use the feature fusion strategy but are limited by the low-order point-to-point fusion methods. In this paper, we propose a novel mutual attention model by fusing attention and contexts from different modalities. We use the non-local attention of one modality to propagate long-range contextual depen…
Shandong Normal University（山东师范大学）；Deakin University（迪肯大学）
For pursuing accurate skeleton-based action recognition, most prior methods use the strategy of combining Graph Convolution Networks (GCNs) with attention-based methods in a serial way. However, they regard the human skeleton as a complete graph, resulting in less variations between different actions (e.g., the connection between the elbow and head in action ``clapping hands''). For this, we propose a novel Contrastive GCN-Transformer Network (ConGT) which fuses the spatial and temporal modules in a parallel way. The ConGT involves two parallel streams: Spatial-Temporal Graph Convolution strea…
Nanyang Technological University（南洋理工大学）；Singapore University of Technology and Design（新加坡科技设计大学）
Person-person mutual action recognition (also referred to as interaction recognition) is an important research branch of human activity analysis. Current solutions in the field -- mainly dominated by CNNs, GCNs and LSTMs -- often consist of complicated architectures and mechanisms to embed the relationships between the two persons on the architecture itself, to ensure the interaction patterns can be properly learned. Our main contribution with this work is by proposing a simpler yet very powerful architecture, named Interaction Relational Network, which utilizes minimal prior knowledge about t…
Bilateral Event Mining and Complementary for Event Stream Super-Resolution
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Peng Cheng Laboratory（鹏城实验室）；School of Computer Science and Engineering, Sun Yat-Sen University（中山大学计算机科学与工程学院）；China Southern Power Grid（中国南方电网）；Xiamen University（厦门大学）
Dual-Stream Collaborative Transformer for Image Captioning
School of Information Engineering, Zhongnan University of Economics and Law（中南财经政法大学信息工程学院）；Information Systems Technology and Design Pillar, Singapore University of Technology and Design（新加坡科技设计大学信息系统技术与设计学院）；Computer Vision Institute, College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机视觉研究院）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（社会人工智能与机器人研究院）
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence（人工智能研究院）
Sign language recognition (SLR) is a challenging problem, involving complex manual features, i.e., hand gestures, and fine-grained non-manual features (NMFs), i.e., facial expression, mouth shapes, etc. Although manual features are dominant, non-manual features also play an important role in the expression of a sign word. Specifically, many sign words convey different meanings due to non-manual features, even though they share the same hand gestures. This ambiguity introduces great challenges in the recognition of sign words. To tackle the above issue, we propose a simple yet effective archite…
Deep learning systems have been reported to achieve state-of-the-art performances in many applications, and a key is the existence of well trained classifiers on benchmark datasets. As a main-stream loss function, the cross entropy can easily lead us to find models which demonstrate severe overfitting behavior. In this paper, we show that the existing cross entropy loss minimization problem essentially learns the label conditional entropy (CE) of the underlying data distribution of the dataset. However, the CE learned in this way does not characterize well the information shared by the label a…
