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）
In the history of knowledge distillation, the focus has once shifted over time from logit-based to feature-based approaches. However, this transition has been revisited with the advent of Decoupled Knowledge Distillation (DKD), which re-emphasizes the importance of logit knowledge through advanced decoupling and weighting strategies. While DKD marks a significant advancement, its underlying mechanisms merit deeper exploration. As a response, we rethink DKD from a predictive distribution perspective. First, we introduce an enhanced version, the Generalized Decoupled Knowledge Distillation (GDKD) loss, which offers a more versatile method for decoupling logits. Then we pay particular attention to the teacher model's predictive distribution and its impact on the gradients of GDKD loss, uncovering two critical insights often overlooked: (1) the partitioning by the top logit considerably improves the interrelationship of non-top logits, and (2) amplifying the focus on the distillation loss of non-top logits enhances the knowledge extraction among them. Utilizing these insights, we further propose a streamlined GDKD algorithm with an efficient partition strategy to handle the multimodality of teacher models' predictive distribution. Our comprehensive experiments conducted on a variety of benchmarks, including CIFAR-100, ImageNet, Tiny-ImageNet, CUB-200-2011, and Cityscapes, demonstrate GDKD's superior performance over both the original DKD and other leading knowledge distillation methods. The code is available at https://github.com/ZaberKo/GDKD.
Horizon Robotics（地平线机器人）；University at Buffalo（布法罗大学）；Tsinghua University（清华大学）
Knowledge distillation is an effective approach to leverage a well-trained network or an ensemble of them, named as the teacher, to guide the training of a student network. The outputs from the teacher network are used as soft labels for supervising the training of a new network. Recent studies \citep{muller2019does,yuan2020revisiting} revealed an intriguing property of the soft labels that making labels soft serves as a good regularization to the student network. From the perspective of statistical learning, regularization aims to reduce the variance, however how bias and variance change is n…
Rethinking Data Distillation: Do Not Overlook Calibration
Texas A&M University（德州农工大学）；Zhejiang University（浙江大学）；Certik；University of Maryland, College Park（马里兰大学帕克分校）；Purdue University（普渡大学）；North Carolina State University（北卡罗来纳州立大学）
Recent researches on unsupervised domain adaptation (UDA) have demonstrated that end-to-end ensemble learning frameworks serve as a compelling option for UDA tasks. Nevertheless, these end-to-end ensemble learning methods often lack flexibility as any modification to the ensemble requires retraining of their frameworks. To address this problem, we propose a flexible ensemble-distillation framework for performing semantic segmentation based UDA, allowing any arbitrary composition of the members in the ensemble while still maintaining its superior performance. To achieve such flexibility, our fr…
School of Computer Science, The University of Sydney（悉尼大学计算机科学学院）
Recent years have witnessed dramatically improvements in the knowledge distillation, which can generate a compact student model for better efficiency while retaining the model effectiveness of the teacher model. Previous studies find that: more accurate teachers do not necessary make for better teachers due to the mismatch of abilities. In this paper, we aim to analysis the phenomenon from the perspective of model calibration. We found that the larger teacher model may be too over-confident, thus the student model cannot effectively imitate. While, after the simple model calibration of the tea…
Rethinking Unsupervised Cross-modal Flow Estimation: Learning from Decoupled Optimization and Consistency Constraint
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）；Ningbo Global Innovation Center, Zhejiang University（浙江大学宁波全球创新中心）；NingboTech University（宁波科技大学）
Rethinking Reverse KL as Adaptive Entropy Distillation
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；School of Science and Technology, Hong Kong Metropolitan University（香港都会大学科技学院）
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 …
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…
Rethinking Dataset Distillation: Hard Truths about Soft Labels
Vision and AI Lab, Indian Institute of Science, Bangalore（印度科学研究院视觉与人工智能实验室，班加罗尔）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；IIT Hyderabad（海得拉巴理工学院）
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…
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（IDEA））
Knowledge Distillation (KD) has developed extensively and boosted various tasks. The classical KD method adds the KD loss to the original cross-entropy (CE) loss. We try to decompose the KD loss to explore its relation with the CE loss. Surprisingly, we find it can be regarded as a combination of the CE loss and an extra loss which has the identical form as the CE loss. However, we notice the extra loss forces the student's relative probability to learn the teacher's absolute probability. Moreover, the sum of the two probabilities is different, making it hard to optimize. To address this issue…
Click-through rate (CTR) Prediction is of great importance in real-world online ads systems. One challenge for the CTR prediction task is to capture the real interest of users from their clicked items, which is inherently biased by presented positions of items, i.e., more front positions tend to obtain higher CTR values. A popular line of existing works focuses on explicitly estimating position bias by result randomization which is expensive and inefficient, or by inverse propensity weighting (IPW) which relies heavily on the quality of the propensity estimation. Another common solution is mod…
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）
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）
Benefiting from masked visual modeling, self-supervised video representation learning has achieved remarkable progress. However, existing methods focus on learning representations from scratch through reconstructing low-level features like raw pixel RGB values. In this paper, we propose masked video distillation (MVD), a simple yet effective two-stage masked feature modeling framework for video representation learning: firstly we pretrain an image (or video) model by recovering low-level features of masked patches, then we use the resulting features as targets for masked feature modeling. For …
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）
BearingPGA-Net: A Lightweight and Deployable Bearing Fault Diagnosis Network via Decoupled Knowledge Distillation and FPGA Acceleration
Harbin Institute of Technology（哈尔滨工业大学）；The Hong Kong Polytechnic University（香港理工大学）；Analog Devices, Inc.（亚德诺公司）；The Chinese University of Hong Kong（香港中文大学）
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…
National University of Defense Technology（国防科技大学）；University of Oulu（奥卢大学）；Nanyang Technological University（南洋理工大学）；Stanford University（斯坦福大学）
Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples by avoiding the overfitting and catastrophic forgetting simultaneously. The current protocol of FSCIL is built by mimicking the general class-incremental learning setting, while it is not totally appropriate due to the different data configuration, i.e., novel classes are all in the limited data regime. In this paper, we rethink the configuration of FSCIL with the open-set hypothesis by reserving the possibility in the first session for incoming categories. To assign better perfo…
KDFlow: A User-Friendly and Efficient Knowledge Distillation Framework for Large Language Models
Key Laboratory of Big Data & Artificial Intelligence in Transportation, (Beijing Jiaotong University), Ministry of Education（大数据与人工智能交通运输联合实验室，（北京交通大学）教育部）；School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China（计算机科学与技术学院，北京交通大学，北京，中国）；Tencent Inc, China（腾讯公司，中国）
The University of Hong Kong（香港大学）；ByteDance Inc.（字节跳动公司）
In this paper, we empirically study how to make the most of low-resolution frames for efficient video recognition. Existing methods mainly focus on developing compact networks or alleviating temporal redundancy of video inputs to increase efficiency, whereas compressing frame resolution has rarely been considered a promising solution. A major concern is the poor recognition accuracy on low-resolution frames. We thus start by analyzing the underlying causes of performance degradation on low-resolution frames. Our key finding is that the major cause of degradation is not information loss in the …
Semi-Supervised Learning (SSL) has shown its strong ability in utilizing unlabeled data when labeled data is scarce. However, most SSL algorithms work under the assumption that the class distributions are balanced in both training and test sets. In this work, we consider the problem of SSL on class-imbalanced data, which better reflects real-world situations. In particular, we decouple the training of the representation and the classifier, and systematically investigate the effects of different data re-sampling techniques when training the whole network including a classifier as well as fine-t…
The Chinese University of Hong Kong（香港中文大学）；SmartMore（思谋科技）；The University of Hong Kong（香港大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. Previous methods limited to the semantic feature and prototype representation suffer from coarse segmentation granularity and train-set overfitting. In this work, we design Hierarchically Decoupled Matching Network (HDMNet) mining pixel-level support correlation based on the transformer architecture. The self-attention modules are used to assist in establishing hierarchical dense features, as a means to accomplish the cascade matching between query and support f…
