Knowledge distillation is to transfer the knowledge from the data learned by the teacher network to the student network, so that the student has the advantage of less parameters and less calculations, and the accuracy is close to the teacher. In this paper, we propose a new distillation method, which contains two transfer distillation strategies and a loss decay strategy. The first transfer strategy is based on channel-wise attention, called Channel Distillation (CD). CD transfers the channel information from the teacher to the student. The second is Guided Knowledge Distillation (GKD). Unlike Knowledge Distillation (KD), which allows the student to mimic each sample's prediction distribution of the teacher, GKD only enables the student to mimic the correct output of the teacher. The last part is Early Decay Teacher (EDT). During the training process, we gradually decay the weight of the distillation loss. The purpose is to enable the student to gradually control the optimization rather than the teacher. Our proposed method is evaluated on ImageNet and CIFAR100. On ImageNet, we achieve 27.68% of top-1 error with ResNet18, which outperforms state-of-the-art methods. On CIFAR100, we achieve surprising result that the student outperforms the teacher. Code is available at https://github.com/zhouzaida/channel-distillation.
Korea Advanced Institute of Science and Technology（韩国科学技术院）；University of California, Berkeley（加州大学伯克利分校）
Deep neural networks with millions of parameters may suffer from poor generalization due to overfitting. To mitigate the issue, we propose a new regularization method that penalizes the predictive distribution between similar samples. In particular, we distill the predictive distribution between different samples of the same label during training. This results in regularizing the dark knowledge (i.e., the knowledge on wrong predictions) of a single network (i.e., a self-knowledge distillation) by forcing it to produce more meaningful and consistent predictions in a class-wise manner. Consequen…
Learning Accurate, Efficient, and Interpretable MLPs on Multiplex Graphs via Node-wise Multi-View Ensemble Distillation
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；Laboratory for Big Data and Decision, National University of Defense Technology（国防科技大学大数据与决策实验室）
Mila（米拉研究所）；Polytechnique Montréal（蒙特利尔高等理工学院）；Peking University（北京大学）；Monash University（莫纳什大学）；Microsoft Research Montréal（微软蒙特利尔研究院）
Knowledge Distillation (KD) is a common method for transferring the ``knowledge'' learned by one machine learning model (the \textit{teacher}) into another model (the \textit{student}), where typically, the teacher has a greater capacity (e.g., more parameters or higher bit-widths). To our knowledge, existing methods overlook the fact that although the student absorbs extra knowledge from the teacher, both models share the same input data -- and this data is the only medium by which the teacher's knowledge can be demonstrated. Due to the difference in model capacities, the student may not bene…
The Chinese University of Hong Kong（香港中文大学）；Tencent AI Lab（腾讯人工智能实验室）
Model compression has been widely adopted to obtain light-weighted deep neural networks. Most prevalent methods, however, require fine-tuning with sufficient training data to ensure accuracy, which could be challenged by privacy and security issues. As a compromise between privacy and performance, in this paper we investigate few shot network compression: given few samples per class, how can we effectively compress the network with negligible performance drop? The core challenge of few shot network compression lies in high estimation errors from the original network during inference, since the…
Knowledge distillation (KD) is a technique to derive optimal performance from a small student network (SN) by distilling knowledge of a large teacher network (TN) and transferring the distilled knowledge to the small SN. Since a role of convolutional neural network (CNN) in KD is to embed a dataset so as to perform a given task well, it is very important to acquire knowledge that considers intra-data relations. Conventional KD methods have concentrated on distilling knowledge in data units. To our knowledge, any KD methods for distilling information in dataset units have not yet been proposed.…
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…
Due to the prosperity of Artificial Intelligence (AI) techniques, more and more backdoors are designed by adversaries to attack Deep Neural Networks (DNNs).Although the state-of-the-art method Neural Attention Distillation (NAD) can effectively erase backdoor triggers from DNNs, it still suffers from non-negligible Attack Success Rate (ASR) together with lowered classification ACCuracy (ACC), since NAD focuses on backdoor defense using attention features (i.e., attention maps) of the same order. In this paper, we introduce a novel backdoor defense framework named Attention Relation Graph Disti…
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）
CLOVA AI Research, NAVER Corp.（NAVER公司CLOVA人工智能研究院）
Knowledge distillation extracts general knowledge from a pre-trained teacher network and provides guidance to a target student network. Most studies manually tie intermediate features of the teacher and student, and transfer knowledge through pre-defined links. However, manual selection often constructs ineffective links that limit the improvement from the distillation. There has been an attempt to address the problem, but it is still challenging to identify effective links under practical scenarios. In this paper, we introduce an effective and efficient feature distillation method utilizing a…
DLink: Distilling Layer-wise and Dominant Knowledge from EEG Foundation Models
Xiamen University（厦门大学）；Nanyang Technological University（南洋理工大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Southeast University（东南大学）
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…
INRIA（法国国家信息与自动化研究所）；Indian Institute of Information Technology, Allahabad（阿拉哈巴德印度信息技术学院）；Université Côte d’Azur（蔚蓝海岸大学）
Multimodal Deep Learning has garnered much interest, and transformers have triggered novel approaches, thanks to the cross-attention mechanism. Here we propose an approach to deal with two key existing challenges: the high computational resource demanded and the issue of missing modalities. We introduce for the first time the concept of knowledge distillation in transformers to use only one modality at inference time. We report a full study analyzing multiple student-teacher configurations, levels at which distillation is applied, and different methodologies. With the best configuration, we im…
Ajou University（亚洲大学）；Hyundai Motor Company（现代汽车公司）；Naver AI Lab（Naver人工智能实验室）
Point-cloud based 3D object detectors recently have achieved remarkable progress. However, most studies are limited to the development of network architectures for improving only their accuracy without consideration of the computational efficiency. In this paper, we first propose an autoencoder-style framework comprising channel-wise compression and decompression via interchange transfer-based knowledge distillation. To learn the map-view feature of a teacher network, the features from teacher and student networks are independently passed through the shared autoencoder; here, we use a compress…
University of Cambridge（剑桥大学）；Avignon University（阿维尼翁大学）；Samsung AI（三星人工智能）
Knowledge distillation has been widely used to compress existing deep learning models while preserving the performance on a wide range of applications. In the specific context of Automatic Speech Recognition (ASR), distillation from ensembles of acoustic models has recently shown promising results in increasing recognition performance. In this paper, we propose an extension of multi-teacher distillation methods to joint CTC-attention end-to-end ASR systems. We also introduce three novel distillation strategies. The core intuition behind them is to integrate the error rate metric to the teacher…
Knowledge distillation (KD) is an effective framework to transfer knowledge from a large-scale teacher to a compact yet well-performing student. Previous KD practices for pre-trained language models mainly transfer knowledge by aligning instance-wise outputs between the teacher and student, while neglecting an important knowledge source, i.e., the gradient of the teacher. The gradient characterizes how the teacher responds to changes in inputs, which we assume is beneficial for the student to better approximate the underlying mapping function of the teacher. Therefore, we propose Gradient Know…
Aragón Institute for Engineering Research (I3A)（阿拉贡工程研究院（I3A））；University of Zaragoza（萨拉戈萨大学）
This paper explores three novel approaches to improve the performance of speaker verification (SV) systems based on deep neural networks (DNN) using Multi-head Self-Attention (MSA) mechanisms and memory layers. Firstly, we propose the use of a learnable vector called Class token to replace the average global pooling mechanism to extract the embeddings. Unlike global average pooling, our proposal takes into account the temporal structure of the input what is relevant for the text-dependent SV task. The class token is concatenated to the input before the first MSA layer, and its state at the out…
Scalable Model Merging with Progressive Layer-wise Distillation
Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）；School of Computer Science, Beijing Institute of Technology（北京理工大学计算机学院）；Shanghai Qizhi Institute（上海启智研究院）
Efficient ANN-Guided Distillation: Aligning Rate-based Features of Spiking Neural Networks through Hybrid Block-wise Replacement
ZJU-UIUC Institute, Zhejiang University（浙江大学ZJU-UIUC联合学院）；College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）
Several solutions for lightweight TTS have shown promising results. Still, they either rely on a hand-crafted design that reaches non-optimum size or use a neural architecture search but often suffer training costs. We present Nix-TTS, a lightweight TTS achieved via knowledge distillation to a high-quality yet large-sized, non-autoregressive, and end-to-end (vocoder-free) TTS teacher model. Specifically, we offer module-wise distillation, enabling flexible and independent distillation to the encoder and decoder module. The resulting Nix-TTS inherited the advantageous properties of being non-au…
Physics-Informed Neural Network Digital Twin for Dynamic Tray-Wise Modeling of Distillation Columns under Transient Operating Conditions
Department of Chemical Engineering, Veer Surendra Sai University of Technology（维杰·苏雷纳·赛大学化学工程系）；Department of Computer Science & Engineering, Veer Surendra Sai University of Technology（维杰·苏雷纳·赛大学计算机科学与工程系）
Yale University（耶鲁大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Automated segmentation in medical image analysis is a challenging task that requires a large amount of manually labeled data. However, most existing learning-based approaches usually suffer from limited manually annotated medical data, which poses a major practical problem for accurate and robust medical image segmentation. In addition, most existing semi-supervised approaches are usually not robust compared with the supervised counterparts, and also lack explicit modeling of geometric structure and semantic information, both of which limit the segmentation accuracy. In this work, we present S…
Weakly Supervised Object Detection (WSOD) has emerged as an effective tool to train object detectors using only the image-level category labels. However, without object-level labels, WSOD detectors are prone to detect bounding boxes on salient objects, clustered objects and discriminative object parts. Moreover, the image-level category labels do not enforce consistent object detection across different transformations of the same images. To address the above issues, we propose a Comprehensive Attention Self-Distillation (CASD) training approach for WSOD. To balance feature learning among all o…
The University of Sydney（悉尼大学）；SenseTime Research（商汤科技研究院）；University of Science and Technology of China（中国科学技术大学）；Peking University（北京大学）
Distilling from the feature maps can be fairly effective for dense prediction tasks since both the feature discriminability and localization priors can be well transferred. However, not every pixel contributes equally to the performance, and a good student should learn from what really matters to the teacher. In this paper, we introduce a learnable embedding dubbed receptive token to localize those pixels of interests (PoIs) in the feature map, with a distillation mask generated via pixel-wise attention. Then the distillation will be performed on the mask via pixel-wise reconstruction. In this…
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…
University at Buffalo（布法罗大学）；United Imaging Intelligence（联影智能）
Federated Learning (FL) is a machine learning paradigm where many local nodes collaboratively train a central model while keeping the training data decentralized. This is particularly relevant for clinical applications since patient data are usually not allowed to be transferred out of medical facilities, leading to the need for FL. Existing FL methods typically share model parameters or employ co-distillation to address the issue of unbalanced data distribution. However, they also require numerous rounds of synchronized communication and, more importantly, suffer from a privacy leakage risk. …
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）
Transformer has been widely-used in many Natural Language Processing (NLP) tasks and the scaled dot-product attention between tokens is a core module of Transformer. This attention is a token-wise design and its complexity is quadratic to the length of sequence, limiting its application potential for long sequence tasks. In this paper, we propose a dimension-wise attention mechanism based on which a novel language modeling approach (namely TensorCoder) can be developed. The dimension-wise attention can reduce the attention complexity from the original $O(N^2d)$ to $O(Nd^2)$, where $N$ is the l…
