Learning group representation is a commonly concerned issue in tasks where the basic unit is a group, set, or sequence. Previously, the research community tries to tackle it by aggregating the elements in a group based on an indicator either defined by humans such as the quality and saliency, or generated by a black box such as the attention score. This article provides a more essential and explicable view. We claim the most significant indicator to show whether the group representation can be benefited from one of its element is not the quality or an inexplicable score, but the discriminability w.r.t. the model. We explicitly design the discrimiability using embedded class centroids on a proxy set. We show the discrimiability knowledge has good properties that can be distilled by a light-weight distillation network and can be generalized on the unseen target set. The whole procedure is denoted as discriminability distillation learning (DDL). The proposed DDL can be flexibly plugged into many group-based recognition tasks without influencing the original training procedures. Comprehensive experiments on various tasks have proven the effectiveness of DDL for both accuracy and efficiency. Moreover, it pushes forward the state-of-the-art results on these tasks by an impressive margin.
CVKD-UDA: Cross-View Knowledge Distillation for 3D Unsupervised Domain Adaptive Segmentation
School of Artificial Intelligence, Nanyang Normal University（南阳师范学院人工智能学院）；School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）；Fujian Key Laboratory of Sensing and Computing for Smart Cities, School of Informatics, Xiamen University（厦门大学信息学院福建省智慧城市感知与计算重点实验室）
Xiamen University（厦门大学）；National University of Singapore（新加坡国立大学）
The large memory and computation consumption in convolutional neural networks (CNNs) has been one of the main barriers for deploying them on resource-limited systems. To this end, most cheap convolutions (e.g., group convolution, depth-wise convolution, and shift convolution) have recently been used for memory and computation reduction but with the specific architecture designing. Furthermore, it results in a low discriminability of the compressed networks by directly replacing the standard convolution with these cheap ones. In this paper, we propose to use knowledge distillation to improve th…
Rethinking Generalizability and Discriminability of Self-Supervised Learning from Evolutionary Game Theory Perspective
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Science（中国科学院自动化研究所）；Tsinghua University（清华大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）
On the Transferability and Discriminability of Repersentation Learning in Unsupervised Domain Adaptation
National Key Laboratory of Space Integrated Information System, Institute of Software Chinese Academy of Sciences（空间信息集成信息系统国家重点实验室，软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；National Key Laboratory of Space Integrated Information System, Department of Computer Science and Technology, Tsinghua University（空间信息集成信息系统国家重点实验室，清华大学计算机科学与技术系）；Artificial Intelligence Thrust, Information Hub, Department of Computer Science & Engineering, School of Engineering, Hong Kong University of Science and Technology（人工智能 thrust，信息枢纽，工程学院计算机科学与工程系，香港科学与技术大学）
Indian Institute of Science（印度科学学院）；Google Research（谷歌研究院）
Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations; while concurrently preserving the task-discriminability knowledge gathered from the labeled source data. However, the requirement of simultaneous access to labeled source and unlabeled target renders them unsuitable for the challenging source-free DA setting. The trivial solution of realizing an effective original to generic domain mapping improves transferability but degrades task discriminability. Upon analyzing the hurdles from both theoretical and empirical sta…
Geometric Understanding of Discriminability and Transferability for Visual Domain Adaptation
School of Mathematics, Sun Yat-Sen University（中山大学数学学院）；School of Statistics and Mathematics, Guangdong University of Finance and Economics（广东财经大学统计与数学学院）；School of Computer Science, Nanjing University of Posts and Telecommunications（南京邮电大学计算机学院）
In video understanding, most cross-modal knowledge distillation (KD) methods are tailored for classification tasks, focusing on the discriminative representation of the trimmed videos. However, action detection requires not only categorizing actions, but also localizing them in untrimmed videos. Therefore, transferring knowledge pertaining to temporal relations is critical for this task which is missing in the previous cross-modal KD frameworks. To this end, we aim at learning an augmented RGB representation for action detection, taking advantage of additional modalities at training time throu…
Despite the empirical success of knowledge distillation, current state-of-the-art methods are computationally expensive to train, which makes them difficult to adopt in practice. To address this problem, we introduce two distinct complementary losses inspired by a cheap entropy-like estimator. These losses aim to maximise the correlation and mutual information between the student and teacher representations. Our method incurs significantly less training overheads than other approaches and achieves competitive performance to the state-of-the-art on the knowledge distillation and cross-model tra…
MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；Boston University（波士顿大学）；IIT Kharagpur（印度理工学院卡拉格普尔分校）
Partial domain adaptation which assumes that the unknown target label space is a subset of the source label space has attracted much attention in computer vision. Despite recent progress, existing methods often suffer from three key problems: negative transfer, lack of discriminability, and domain invariance in the latent space. To alleviate the above issues, we develop a novel 'Select, Label, and Mix' (SLM) framework that aims to learn discriminative invariant feature representations for partial domain adaptation. First, we present an efficient "select" module that automatically filters out t…
Representation knowledge distillation aims at transferring rich information from one model to another. Common approaches for representation distillation mainly focus on the direct minimization of distance metrics between the models' embedding vectors. Such direct methods may be limited in transferring high-order dependencies embedded in the representation vectors, or in handling the capacity gap between the teacher and student models. Moreover, in standard knowledge distillation, the teacher is trained without awareness of the student's characteristics and capacity. In this paper, we explore t…
Tampere University（坦佩雷大学）；Aarhus University（奥胡斯大学）
Knowledge Distillation refers to a class of methods that transfers the knowledge from a teacher network to a student network. In this paper, we propose Sparse Representation Matching (SRM), a method to transfer intermediate knowledge obtained from one Convolutional Neural Network (CNN) to another by utilizing sparse representation learning. SRM first extracts sparse representations of the hidden features of the teacher CNN, which are then used to generate both pixel-level and image-level labels for training intermediate feature maps of the student network. We formulate SRM as a neural processi…
The downstream accuracy of self-supervised methods is tightly linked to the proxy task solved during training and the quality of the gradients extracted from it. Richer and more meaningful gradients updates are key to allow self-supervised methods to learn better and in a more efficient manner. In a typical self-distillation framework, the representation of two augmented images are enforced to be coherent at the global level. Nonetheless, incorporating local cues in the proxy task can be beneficial and improve the model accuracy on downstream tasks. This leads to a dual objective in which, on …
Knowledge distillation (KD), which can efficiently transfer knowledge from a cumbersome network (teacher) to a compact network (student), has demonstrated its advantages in some computer vision applications. The representation of knowledge is vital for knowledge transferring and student learning, which is generally defined in hand-crafted manners or uses the intermediate features directly. In this paper, we propose a model-agnostic meta knowledge distillation method under the teacher-student architecture for the single image super-resolution task. It provides a more flexible and accurate way t…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Kuaishou Technology（快手科技）；Y-tech
We address the challenging problem of learning motion representations using deep models for video recognition. To this end, we make use of attention modules that learn to highlight regions in the video and aggregate features for recognition. Specifically, we propose to leverage output attention maps as a vehicle to transfer the learned representation from a motion (flow) network to an RGB network. We systematically study the design of attention modules, and develop a novel method for attention distillation. Our method is evaluated on major action benchmarks, and consistently improves the perfo…
Open Vocabulary 3D Scene Understanding via Geometry Guided Self-Distillation
The Hong Kong Polytechnic University（香港理工大学）；Centre for Artificial Intelligence and Robotics, HKISI, CAS（中国科学院香港智能研究院人工智能与机器人中心）；State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)（中国科学院大学人工智能学院）
University of Science and Technology of China（中国科学技术大学）；The University of Adelaide（阿德莱德大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）；Shanghai Artificial Intelligent Laboratory（上海人工智能实验室）
Recent progresses on self-supervised 3D human action representation learning are largely attributed to contrastive learning. However, in conventional contrastive frameworks, the rich complementarity between different skeleton modalities remains under-explored. Moreover, optimized with distinguishing self-augmented samples, models struggle with numerous similar positive instances in the case of limited action categories. In this work, we tackle the aforementioned problems by introducing a general Inter- and Intra-modal Mutual Distillation (I$^2$MD) framework. In I$^2$MD, we first re-formulate t…
In this work we propose a technique that transfers supervision between images from different modalities. We use learned representations from a large labeled modality as a supervisory signal for training representations for a new unlabeled paired modality. Our method enables learning of rich representations for unlabeled modalities and can be used as a pre-training procedure for new modalities with limited labeled data. We show experimental results where we transfer supervision from labeled RGB images to unlabeled depth and optical flow images and demonstrate large improvements for both these c…
The University of Sydney（悉尼大学）；SenseTime Group Limited（商汤集团有限公司）
Knowledge distillation aims to transfer representation ability from a teacher model to a student model. Previous approaches focus on either individual representation distillation or inter-sample similarity preservation. While we argue that the inter-sample relation conveys abundant information and needs to be distilled in a more effective way. In this paper, we propose a novel knowledge distillation method, namely Complementary Relation Contrastive Distillation (CRCD), to transfer the structural knowledge from the teacher to the student. Specifically, we estimate the mutual relation in an anch…
National Central University（国立中央大学）；Thai Nguyen University（太原大学）
Knowledge distillation is an effective transfer of knowledge from a heavy network (teacher) to a small network (student) to boost students' performance. Self-knowledge distillation, the special case of knowledge distillation, has been proposed to remove the large teacher network training process while preserving the student's performance. This paper introduces a novel Self-knowledge distillation approach via Siamese representation learning, which minimizes the difference between two representation vectors of the two different views from a given sample. Our proposed method, SKD-SRL, utilizes bo…
Northwestern Polytechnical University（西北工业大学）；Air Force Engineering University（空军工程大学）；wrnch（wrnch公司）；Nanchang University（南昌大学）
The target representation learned by convolutional neural networks plays an important role in Thermal Infrared (TIR) tracking. Currently, most of the top-performing TIR trackers are still employing representations learned by the model trained on the RGB data. However, this representation does not take into account the information in the TIR modality itself, limiting the performance of TIR tracking. To solve this problem, we propose to distill representations of the TIR modality from the RGB modality with Cross-Modal Distillation (CMD) on a large amount of unlabeled paired RGB-TIR data. We take…
Beijing University of Posts and Telecommunications（北京邮电大学）；Beijing Key Laboratory of Space-ground Interconnection and Convergence（北京天地互联与融合重点实验室）
Online knowledge distillation conducts knowledge transfer among all student models to alleviate the reliance on pre-trained models. However, existing online methods rely heavily on the prediction distributions and neglect the further exploration of the representational knowledge. In this paper, we propose a novel Multi-scale Feature Extraction and Fusion method (MFEF) for online knowledge distillation, which comprises three key components: Multi-scale Feature Extraction, Dual-attention and Feature Fusion, towards generating more informative feature maps for distillation. The multiscale feature…
A Dynamic Graph CNN with Cross-Representation Distillation for Event-Based Recognition
National Engineering Research Center for E-Learning, Central China Normal University（华中师范大学国家数字化学习工程技术研究中心）；Beijing University of Technology（北京工业大学）；Southeast University（东南大学）；City University of Hong Kong（香港城市大学）
Rethinking Representations for Cross-Domain Infrared Small Target Detection: A Generalizable Perspective from the Frequency Domain
Department of Mathematics, Hong Kong Baptist University（香港浸会大学数学系）；School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）；Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）
Knowledge distillation (KD) achieves promising results on the challenging problem of unsupervised anomaly detection (AD).The representation discrepancy of anomalies in the teacher-student (T-S) model provides essential evidence for AD. However, using similar or identical architectures to build the teacher and student models in previous studies hinders the diversity of anomalous representations. To tackle this problem, we propose a novel T-S model consisting of a teacher encoder and a student decoder and introduce a simple yet effective "reverse distillation" paradigm accordingly. Instead of re…
CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation
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）
As GAN-based video and image manipulation technologies become more sophisticated and easily accessible, there is an urgent need for effective deepfake detection technologies. Moreover, various deepfake generation techniques have emerged over the past few years. While many deepfake detection methods have been proposed, their performance suffers from new types of deepfake methods on which they are not sufficiently trained. To detect new types of deepfakes, the model should learn from additional data without losing its prior knowledge about deepfakes (catastrophic forgetting), especially when new…
CLIDD: Cross-Layer Independent Deformable Description for Efficient and Discriminative Local Feature Representation
School of Astronautics, Harbin Institute of Technology, China（航天学院，哈尔滨工业大学，中国）；State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI), China（通用人工智能国家重点实验室，北京通用人工智能研究院（BIGAI），中国）
Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation
School of Artificial Intelligence, Xidian University, China（西安电子科技大学人工智能学院）；Department of Information Engineering and Computer Science, University of Trento, Italy（特伦托大学信息工程与计算机科学系）；Department of Automation, Tsinghua University, China（清华大学自动化系）；School of Computer Science and Information Engineering, Hefei University of Technology, China（合肥工业大学计算机科学与信息工程学院）
Key Laboratory for Information Science of Electromagnetic Waves, Ministry of Education, Fudan University（复旦大学电磁波信息科学教育部重点实验室）；Discipline and Technology Center of Microwave Vision Intelligent Sensing, Fudan University（复旦大学微波视觉智能感知学科与技术中心）
Simon Fraser University（西蒙弗雷泽大学）；Borealis AI（Borealis人工智能研究院）
Knowledge distillation is a widely applicable technique for training a student neural network under the guidance of a trained teacher network. For example, in neural network compression, a high-capacity teacher is distilled to train a compact student; in privileged learning, a teacher trained with privileged data is distilled to train a student without access to that data. The distillation loss determines how a teacher's knowledge is captured and transferred to the student. In this paper, we propose a new form of knowledge distillation loss that is inspired by the observation that semantically…
The primary goal of knowledge distillation (KD) is to encapsulate the information of a model learned from a teacher network into a student network, with the latter being more compact than the former. Existing work, e.g., using Kullback-Leibler divergence for distillation, may fail to capture important structural knowledge in the teacher network and often lacks the ability for feature generalization, particularly in situations when teacher and student are built to address different classification tasks. We propose Wasserstein Contrastive Representation Distillation (WCoRD), which leverages both…
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Google Research（谷歌研究院）
Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from one sensory modality to a second, or ensembling a collection of models into a single estimator. Knowledge distillation, the standard approach to these problems, minimizes the KL divergence between the probabilistic outputs of a teacher and student network. We demonstrate that this objective ignores important structural knowledge of the teacher network. This motivates an alternative objective by which we train a stud…
Is Contrastive Distillation Enough for Learning Comprehensive 3D Representations?
School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China（上海大学机械与自动化工程学院）；Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China（香港城市大学计算机科学系）
Arizona State University（亚利桑那州立大学）；Microsoft Corporation（微软公司）
This paper is concerned with self-supervised learning for small models. The problem is motivated by our empirical studies that while the widely used contrastive self-supervised learning method has shown great progress on large model training, it does not work well for small models. To address this problem, we propose a new learning paradigm, named SElf-SupErvised Distillation (SEED), where we leverage a larger network (as Teacher) to transfer its representational knowledge into a smaller architecture (as Student) in a self-supervised fashion. Instead of directly learning from unlabeled data, w…
Real-world imagery is often characterized by a significant imbalance of the number of images per class, leading to long-tailed distributions. An effective and simple approach to long-tailed visual recognition is to learn feature representations and a classifier separately, with instance and class-balanced sampling, respectively. In this work, we introduce a new framework, by making the key observation that a feature representation learned with instance sampling is far from optimal in a long-tailed setting. Our main contribution is a new training method, referred to as Class-Balanced Distillati…
Recent research has found that knowledge distillation can be effective in reducing the size of a network and in increasing generalization. A pre-trained, large teacher network, for example, was shown to be able to bootstrap a student model that eventually outperforms the teacher in a limited label environment. Despite these advances, it still is relatively unclear \emph{why} this method works, that is, what the resulting student model does 'better'. To address this issue, here, we utilize two non-linear, low-dimensional embedding methods (t-SNE and IVIS) to visualize representation spaces of d…
Beyond Modality Collapse: Representations Blending for Multimodal Dataset Distillation
Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore（前沿人工智能研究中心，科技研究局，新加坡）；Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore（高性能计算研究所，科技研究局，新加坡）；National University of Singapore, Singapore（新加坡国立大学）；Zhejiang University, China（浙江大学）
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Amazon Prime Video（亚马逊Prime Video）
The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To address this challenge, we introduce a novel training framework based on cross-modal contrastive learning that uses progressive self-distillation and soft image-text alignments to more efficiently learn robust representations from noisy data. Our model distills its own knowledge to dynamically generate soft-alignment targets for a subset of images and captio…
On the Discriminability of Self-Supervised Representation Learning
University of Chinese Academy of Sciences（中国科学院大学）；National Key Laboratory of Space Integrated Information System, Institute of Software Chinese Academy of Sciences（空间信息集成系统国家重点实验室，中国科学院软件研究所）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Hong Kong University of Science and Technology（香港科技大学）
