Heterogeneous distillation is an effective way to transfer knowledge from cross-architecture teacher models to student models. However, existing heterogeneous distillation methods do not take full advantage of the dark knowledge hidden in the teacher's output, limiting their performance.To this end, we propose a novel framework named Multi-Level Decoupled Relational Knowledge Distillation (MLDR-KD) to unleash the potential of relational distillation in heterogeneous distillation. Concretely, we first introduce Decoupled Finegrained Relation Alignment (DFRA) in both logit and feature levels to balance the trade-off between distilled dark knowledge and the confidence in the correct category of the heterogeneous teacher model. Then, Multi-Scale Dynamic Fusion (MSDF) module is applied to dynamically fuse the projected logits of multiscale features at different stages in student model, further improving performance of our method in feature level. We verify our method on four architectures (CNNs, Transformers, MLPs and Mambas), two datasets (CIFAR-100 and Tiny-ImageNet). Compared with the best available method, our MLDR-KD improves student model performance with gains of up to 4.86% on CIFAR-100 and 2.78% on Tiny-ImageNet datasets respectively, showing robustness and generality in heterogeneous distillation. Code will be released soon.
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Horizon Robotics（地平线机器人）；Wuhan University（武汉大学）
Current Knowledge Distillation (KD) methods for semantic segmentation often guide the student to mimic the teacher's structured information generated from individual data samples. However, they ignore the global semantic relations among pixels across various images that are valuable for KD. This paper proposes a novel Cross-Image Relational KD (CIRKD), which focuses on transferring structured pixel-to-pixel and pixel-to-region relations among the whole images. The motivation is that a good teacher network could construct a well-structured feature space in terms of global pixel dependencies. CI…
Rectified Decoupled Dataset Distillation: A Closer Look for Fair and Comprehensive Evaluation
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities
Academy for Engineering and Technology, Fudan University（复旦大学工程技术学院）；Jilin Provincial Key Laboratory of Intelligence Science and Engineering（吉林省智能科学与工程重点实验室）；Engineering Research Center of AI and Robotics, Ministry of Education（教育部人工智能与机器人工程研究中心）
Nanjing University of Science and Technology（南京理工大学）
Human multimodal emotion recognition (MER) aims to perceive human emotions via language, visual and acoustic modalities. Despite the impressive performance of previous MER approaches, the inherent multimodal heterogeneities still haunt and the contribution of different modalities varies significantly. In this work, we mitigate this issue by proposing a decoupled multimodal distillation (DMD) approach that facilitates flexible and adaptive crossmodal knowledge distillation, aiming to enhance the discriminative features of each modality. Specially, the representation of each modality is decouple…
Despite the success that metric learning based approaches have achieved in few-shot learning, recent works reveal the ineffectiveness of their episodic training mode. In this paper, we point out two potential reasons for this problem: 1) the random episodic labels can only provide limited supervision information, while the relatedness information between the query and support samples is not fully exploited; 2) the meta-learner is usually constrained by the limited contextual information of the local episode. To overcome these problems, we propose a new Global Relatedness Decoupled-Distillation…
Displacement Preserving Relational Distillation for Robust Medical Segmentation
Bowling Green State University（鲍灵格林州立大学）；The University of Findlay（芬德利大学）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；University of Toronto（多伦多大学）；University of Houston - Clear Lake（休斯顿大学清水湖分校）；UTHealth Houston（德克萨斯大学健康科学中心休斯顿分校）
Knowledge distillation aims at transferring knowledge acquired in one model (a teacher) to another model (a student) that is typically smaller. Previous approaches can be expressed as a form of training the student to mimic output activations of individual data examples represented by the teacher. We introduce a novel approach, dubbed relational knowledge distillation (RKD), that transfers mutual relations of data examples instead. For concrete realizations of RKD, we propose distance-wise and angle-wise distillation losses that penalize structural differences in relations. Experiments conduct…
Decoupled Hierarchical Distillation for Multimodal Emotion Recognition
School of Computer Science and Engineering, and the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Southeast University（计算机科学与工程学院，新一代人工智能技术及跨学科应用重点实验室，东南大学）；School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院，南京理工大学）；Institute of Intelligent Information Processing, Taizhou University（智能信息处理研究院，台州大学）；School of Engineering Science, University of Chinese Academy of Sciences（工程科学学院，中国科学院大学）；Peng Cheng Laboratory（鹏城实验室）；School of Computer Science and Engineering, Nanyang Technological University（计算机科学与工程学院，南洋理工大学）
State-of-the-art distillation methods are mainly based on distilling deep features from intermediate layers, while the significance of logit distillation is greatly overlooked. To provide a novel viewpoint to study logit distillation, we reformulate the classical KD loss into two parts, i.e., target class knowledge distillation (TCKD) and non-target class knowledge distillation (NCKD). We empirically investigate and prove the effects of the two parts: TCKD transfers knowledge concerning the "difficulty" of training samples, while NCKD is the prominent reason why logit distillation works. More …
GaitKD: A Universal Decoupled Distillation Framework for Efficient Gait Recognition
The City University of New York（纽约城市大学）；Wuhan University（武汉大学）；Beijing Jiaotong University（北京交通大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Oulu（奥卢大学）
Privileged Lesion-Context Relational Distillation for Mask-Free Skin Lesion Classification
Victoria University（维多利亚大学）；Bangaldesh University of Business and Technology（孟加拉国商业与技术大学）；Daffodil Institute of Information Technology（达芙妮信息技术学院）；American International University-Bangladesh (AIUB)（孟加拉国美国国际大学）；Multimedia University（多媒体大学）
Airdoc LLC（鹰瞳科技）；Monash University（莫纳什大学）；Harbin Engineering University（哈尔滨工程大学）；The University of Sydney（悉尼大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
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 d…
Rethinking Decoupled Knowledge Distillation: A Predictive Distribution Perspective
Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University（数据科学与人工智能系，香港理工大学）；Department of Computing, The Hong Kong Polytechnic University（计算系，香港理工大学）；The Hong Kong Polytechnic University Shenzhen Research Institute（香港理工大学深圳研究院）
Nanyang Technological University（南洋理工大学）；University of British Columbia（不列颠哥伦比亚大学）；Vancouver Coast Health Research Institute（温哥华海岸健康研究所）；BC Cancer（不列颠哥伦比亚癌症中心）
Skin cancer is one of the most common types of malignancy, affecting a large population and causing a heavy economic burden worldwide. Over the last few years, computer-aided diagnosis has been rapidly developed and make great progress in healthcare and medical practices due to the advances in artificial intelligence. However, most studies in skin cancer detection keep pursuing high prediction accuracies without considering the limitation of computing resources on portable devices. In this case, knowledge distillation (KD) has been proven as an efficient tool to help improve the adaptability o…
Object detection has achieved promising performance on clean datasets, but how to achieve better tradeoff between the adversarial robustness and clean precision is still under-explored. Adversarial training is the mainstream method to improve robustness, but most of the works will sacrifice clean precision to gain robustness than standard training. In this paper, we propose Unified Decoupled Feature Alignment (UDFA), a novel fine-tuning paradigm which achieves better performance than existing methods, by fully exploring the combination between self-knowledge distillation and adversarial traini…
Relational Knowledge Distillation Brings DNN Representations Close Enough to Humans to Be Aligned Without Supervision
Graduate School of Arts and Sciences, The University of Tokyo（东京大学文学部与科学研究科）；Graduate School of Engineering Science, The University of Osaka（大阪大学工程科学研究科）
Southern University of Science and Technology（南方科技大学）；The Chinese University of Hong Kong（香港中文大学）；Xiamen University（厦门大学）；City University of Hong Kong（香港城市大学）
The amount of medical images for training deep classification models is typically very scarce, making these deep models prone to overfit the training data. Studies showed that knowledge distillation (KD), especially the mean-teacher framework which is more robust to perturbations, can help mitigate the over-fitting effect. However, directly transferring KD from computer vision to medical image classification yields inferior performance as medical images suffer from higher intra-class variance and class imbalance. To address these issues, we propose a novel Categorical Relation-preserving Contr…
FD$^2$: A Dedicated Framework for Fine-Grained Dataset Distillation
Zhejiang University（浙江大学）；Hokkaido University（北海道大学）；The University of Queensland（昆士兰大学）；Shanghai AI Laboratory（上海人工智能实验室）；Dalian University of Technology（大连理工大学）
Clemson University（克莱姆森大学）；University at Buffalo（布法罗大学）
Knowledge distillation (KD) has become an important technique for model compression and knowledge transfer. In this work, we first perform a comprehensive analysis of the knowledge transferred by different KD methods. We demonstrate that traditional KD methods, which minimize the KL divergence of softmax outputs between networks, are related to the knowledge alignment of an individual sample only. Meanwhile, recent contrastive learning-based KD methods mainly transfer relational knowledge between different samples, namely, knowledge correlation. While it is important to transfer the full knowl…
Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers
School of Electronic and Information Engineering, South China University of Technology（华南理工大学电子与信息工程学院）；Peng Cheng Laboratory（鹏城实验室）；Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Adobe Research（奥多比研究院）；Arizona State University（亚利桑那州立大学）
For tasks involving language and vision, the current state-of-the-art methods tend not to leverage any additional information that might be present to gather relevant (commonsense) knowledge. A representative task is Visual Question Answering where large diagnostic datasets have been proposed to test a system's capability of answering questions about images. The training data is often accompanied by annotations of individual object properties and spatial locations. In this work, we take a step towards integrating this additional privileged information in the form of spatial knowledge to aid in…
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）
Zhejiang University（浙江大学）；University of Science and Technology of China（中国科学技术大学）；Tsinghua University（清华大学）
Knowledge Distillation (KD) aims at transferring knowledge from a larger well-optimized teacher network to a smaller learnable student network.Existing KD methods have mainly considered two types of knowledge, namely the individual knowledge and the relational knowledge. However, these two types of knowledge are usually modeled independently while the inherent correlations between them are largely ignored. It is critical for sufficient student network learning to integrate both individual knowledge and relational knowledge while reserving their inherent correlation. In this paper, we propose t…
Local Dense Logit Relations for Enhanced Knowledge Distillation
Northeastern University, China（东北大学）；South China Normal University, China（华南师范大学）；Shenzhen Institutes of Advanced Technology, CAS, China（深圳先进技术研究院）；The Chinese University of Hong Kong, Hong Kong, China（香港中文大学）
The University of Tokyo（东京大学）；National Institute of Informatics（国立信息学研究所）
Recent deep metric learning (DML) methods typically leverage solely class labels to keep positive samples far away from negative ones. However, this type of method normally ignores the crucial knowledge hidden in the data (e.g., intra-class information variation), which is harmful to the generalization of the trained model. To alleviate this problem, in this paper we propose Online Batch Diffusion-based Self-Distillation (OBD-SD) for DML. Specifically, we first propose a simple but effective Progressive Self-Distillation (PSD), which distills the knowledge progressively from the model itself d…
PSM: Dataset Distillation Based on Precise Statistical Matching by Difficulty
Zhejiang University（浙江大学）；Hokkaido University（北海道大学）；The University of Queensland（昆士兰大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；National University of Singapore（新加坡国立大学）；Dalian University of Technology（大连理工大学）
