Decoupling Dark Knowledge via Block-wise Logit Distillation for Feature-level Alignment
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息与电子工程学院）；ZJU-UIUC Institute, Zhejiang University（浙江大学-伊利诺伊大学厄巴纳-香槟分校联合学院）
Knowledge Distillation (KD), a learning manner with a larger teacher network guiding a smaller student network, transfers dark knowledge from the teacher to the student via logits or intermediate features, with the aim of producing a well-performed lightweight model. Notably, many subsequent feature-based KD methods outperformed the earliest logit-based KD method and iteratively generated numerous state-of-the-art distillation methods. Nevertheless, recent work has uncovered the potential of the logit-based method, bringing the simple KD form based on logits back into the limelight. Features or logits? They partially implement the KD with entirely distinct perspectives; therefore, choosing between logits and features is not straightforward. This paper provides a unified perspective of feature alignment in order to obtain a better comprehension of their fundamental distinction. Inheriting the design philosophy and insights of feature-based and logit-based methods, we introduce a block-wise logit distillation framework to apply implicit logit-based feature alignment by gradually replacing teacher's blocks as intermediate stepping-stone models to bridge the gap between the student and the teacher. Our method obtains comparable or superior results to state-of-the-art distillation methods. This paper demonstrates the great potential of combining logit and features, and we hope it will inspire future research to revisit KD from a higher vantage point.
Knowledge distillation aims to transfer knowledge to the student model by utilizing the predictions/features of the teacher model, and feature-based distillation has recently shown its superiority over logit-based distillation. However, due to the cumbersome computation and storage of extra feature transformation, the training overhead of feature-based methods is much higher than that of logit-based distillation. In this work, we revisit the logit-based knowledge distillation, and observe that the existing logit-based distillation methods treat the prediction logits only in the instance level,…
Samsung Research America（三星美国研究院）；Georgia Institute of Technology（佐治亚理工学院）
Knowledge distillation (KD) is a substantial strategy for transferring learned knowledge from one neural network model to another. A vast number of methods have been developed for this strategy. While most method designs a more efficient way to facilitate knowledge transfer, less attention has been put on comparing the effect of knowledge sources such as features, logits, and gradients. This work provides a new perspective to motivate a set of knowledge distillation strategies by approximating the classical KL-divergence criteria with different knowledge sources, making a systematic comparison…
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）
LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit Calibration
Apurba-NSU R&D Lab, North South University, Bangladesh（阿普尔巴-NSU研发实验室，北南大学，孟加拉国）；Pluralis Research（普拉尔西斯研究）；Data61-CSIRO, Australia & Australian National University, Australia（Data61-CSIRO，澳大利亚及澳大利亚国立大学，澳大利亚）；Apurba Technologies, Sunnyvale, CA 94085, USA（阿普尔巴技术，硅谷，加州94085，美国）
State Key Laboratory of Blockchain and Data Security, Zhejiang University（区块链与数据安全国家重点实验室，浙江大学）；School of Software Technology, Zhejiang University（浙江大学软件技术学院）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江区）区块链与数据安全研究院）；University at Buffalo, State University of New York（纽约州立大学布法罗分校）；NingboTech University（宁波科技学院）
Knowledge distillation (KD), transferring knowledge from a cumbersome teacher model to a lightweight student model, has been investigated to design efficient neural architectures. Generally, the objective function of KD is the Kullback-Leibler (KL) divergence loss between the softened probability distributions of the teacher model and the student model with the temperature scaling hyperparameter tau. Despite its widespread use, few studies have discussed the influence of such softening on generalization. Here, we theoretically show that the KL divergence loss focuses on the logit matching when…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen Campus（中山大学深圳校区网络空间安全学院）
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）
Peak-Controlled Logits Poisoning Attack in Federated Distillation
School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机与信息技术学院）；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）
Shanghai Jiao Tong University（上海交通大学）；UC Santa Cruz（加州大学圣克鲁兹分校）；The University of Hong Kong（香港大学）
Federated learning (FL) is a distributed learning paradigm that enables multiple clients to collaboratively learn a shared global model. Despite the recent progress, it remains challenging to deal with heterogeneous data clients, as the discrepant data distributions usually prevent the global model from delivering good generalization ability on each participating client. In this paper, we propose CD^2-pFed, a novel Cyclic Distillation-guided Channel Decoupling framework, to personalize the global model in FL, under various settings of data heterogeneity. Different from previous works which est…
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 …
Collaborative Innovation Center of Railway Traffic Safety, Beijing Jiaotong University（北京交通大学轨道交通运行安全协同创新中心）；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）
Grouped Knowledge Distillation for Deep Face Recognition
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人中心）
Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation
State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences（机器人与智能系统国家重点实验室，沈阳自动化研究所，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）
Remote sensing (RS) image scene classification task faces many challenges due to the interference from different characteristics of different geographical elements. To solve this problem, we propose a multi-branch ensemble network to enhance the feature representation ability by fusing features in final output logits and intermediate feature maps. However, simply adding branches will increase the complexity of models and decline the inference efficiency. On this issue, we embed self-distillation (SD) method to transfer knowledge from ensemble network to main-branch in it. Through optimizing wi…
OPPO Research Institute（OPPO研究院）；Fudan University（复旦大学）
Knowledge distillation (KD) has been extensively studied in single-label image classification. However, its efficacy for multi-label classification remains relatively unexplored. In this study, we firstly investigate the effectiveness of classical KD techniques, including logit-based and feature-based methods, for multi-label classification. Our findings indicate that the logit-based method is not well-suited for multi-label classification, as the teacher fails to provide inter-category similarity information or regularization effect on student model's training. Moreover, we observe that featu…
From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels
Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；International Digital Economy Academy (IDEA)（国际数字经济研究院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Heterogeneous Knowledge Distillation via Geometry Decoupling and Momentum-Aware Gradient Regulation
School of Computer and Mathematics, Central South University of Forestry and Technology（中南林业科技大学计算机与数学学院）；College of Computer Science and Technology, and the Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology（国防科技大学计算机科学与技术学院及前沿装备数字化软件实验室）
JDCNet: Confidence-Gated Privileged-Modality Distillation for Cost-Preserving X-ray Inference
Auckland University of Technology（奥克兰技术大学）；Guilin University of Electronic Technology（桂林电子科技大学）；Hikvision Technology Co., Ltd（海康威视技术有限公司）；Hebei University of Technology（河北工业大学）
