Knowledge distillation (KD) has been proven to be a simple and effective tool for training compact models. Almost all KD variants for dense prediction tasks align the student and teacher networks' feature maps in the spatial domain, typically by minimizing point-wise and/or pair-wise discrepancy. Observing that in semantic segmentation, some layers' feature activations of each channel tend to encode saliency of scene categories (analogue to class activation mapping), we propose to align features channel-wise between the student and teacher networks. To this end, we first transform the feature map of each channel into a probabilty map using softmax normalization, and then minimize the Kullback-Leibler (KL) divergence of the corresponding channels of the two networks. By doing so, our method focuses on mimicking the soft distributions of channels between networks. In particular, the KL divergence enables learning to pay more attention to the most salient regions of the channel-wise maps, presumably corresponding to the most useful signals for semantic segmentation. Experiments demonstrate that our channel-wise distillation outperforms almost all existing spatial distillation methods for semantic segmentation considerably, and requires less computational cost during training. We consistently achieve superior performance on three benchmarks with various network structures. Code is available at: https://git.io/Distiller
The University of Adelaide（阿德莱德大学）；Nanjing Institute of Advanced Artificial Intelligence（南京高等人工智能研究院）；Microsoft Research（微软研究院）
In this work, we consider transferring the structure information from large networks to compact ones for dense prediction tasks in computer vision. Previous knowledge distillation strategies used for dense prediction tasks often directly borrow the distillation scheme for image classification and perform knowledge distillation for each pixel separately, leading to sub-optimal performance. Here we propose to distill structured knowledge from large networks to compact networks, taking into account the fact that dense prediction is a structured prediction problem. Specifically, we study two struc…
While self-supervised representation learning (SSL) has proved to be effective in the large model, there is still a huge gap between the SSL and supervised method in the lightweight model when following the same solution. We delve into this problem and find that the lightweight model is prone to collapse in semantic space when simply performing instance-wise contrast. To address this issue, we propose a relation-wise contrastive paradigm with Relation Knowledge Distillation (ReKD). We introduce a heterogeneous teacher to explicitly mine the semantic information and transferring a novel relatio…
Centerness-based Instance-aware Knowledge Distillation with Task-wise Mutual Lifting for Object Detection on Drone Imagery
Beihang University（北京航空航天大学）；State Key Laboratory of Software Development Environment（软件开发环境国家重点实验室）；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
Hangzhou Dianzi University（杭州电子科技大学）；Baidu Inc.（百度公司）；Zhejiang International Studies University（浙江外国语学院）
This paper proposes an approach to Dense Video Captioning (DVC) without pairwise event-sentence annotation. First, we adopt the knowledge distilled from relevant and well solved tasks to generate high-quality event proposals. Then we incorporate contrastive loss and cycle-consistency loss typically applied to cross-modal retrieval tasks to build semantic matching between the proposals and sentences, which are eventually used to train the caption generation module. In addition, the parameters of matching module are initialized via pre-training based on annotated images to improve the matching p…
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）
Towards Customized Knowledge Distillation for Chip-Level Dense Image Predictions
Department of Electronic and Computer Engineering, HKUST, Hong Kong, China（电子与计算机工程系，香港科技大学，香港，中国）；Department of Computer Science and Engineering, HKUST, Hong Kong, China（计算机科学与工程系，香港科技大学，香港，中国）
It is challenging to bridge the performance gap between Binary CNN (BCNN) and Floating point CNN (FCNN). We observe that, this performance gap leads to substantial residuals between intermediate feature maps of BCNN and FCNN. To minimize the performance gap, we enforce BCNN to produce similar intermediate feature maps with the ones of FCNN. This training strategy, i.e., optimizing each binary convolutional block with block-wise distillation loss derived from FCNN, leads to a more effective optimization to BCNN. It also motivates us to update the binary convolutional block architecture to facil…
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…
With the success of deep neural networks, knowledge distillation which guides the learning of a small student network from a large teacher network is being actively studied for model compression and transfer learning. However, few studies have been performed to resolve the poor learning issue of the student network when the student and teacher model sizes significantly differ. In this paper, we propose a densely guided knowledge distillation using multiple teacher assistants that gradually decreases the model size to efficiently bridge the large gap between the teacher and student networks. To…
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…
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）
Lightweight Self-Knowledge Distillation with Multi-source Information Fusion
Northeastern University at Qinhuangdao（东北大学秦皇岛分校）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Chongqing University of Posts and Telecommunications（重庆邮电大学）
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）
Holistic White-light Polyp Classification via Alignment-free Dense Distillation of Auxiliary Optical Chromoendoscopy
Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology（光电国立实验室、华中科技大学）；Changzhou United Imaging Surgical Co., Ltd（常州联合影像手术有限公司）；Tongji Medical College of Huazhong University of Science and Technology（华中科技大学同济医学院）
Dense Depth Distillation with Out-of-Distribution Simulated Images
Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人研究院）；South China Normal University（华南师范大学）；METU（中东技术大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Knowledge Distillation (KD) based methods adopt the one-way Knowledge Transfer (KT) scheme in which training a lower-capacity student network is guided by a pre-trained high-capacity teacher network. Recently, Deep Mutual Learning (DML) presented a two-way KT strategy, showing that the student network can be also helpful to improve the teacher network. In this paper, we propose Dense Cross-layer Mutual-distillation (DCM), an improved two-way KT method in which the teacher and student networks are trained collaboratively from scratch. To augment knowledge representation learning, well-designed …
This paper tackles the problem of semi-supervised video object segmentation on resource-constrained devices, such as mobile phones. We formulate this problem as a distillation task, whereby we demonstrate that small space-time-memory networks with finite memory can achieve competitive results with state of the art, but at a fraction of the computational cost (32 milliseconds per frame on a Samsung Galaxy S22). Specifically, we provide a theoretically grounded framework that unifies knowledge distillation with supervised contrastive representation learning. These models are able to jointly 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…
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…
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…
Henan University of Chinese Medicine（河南中医药大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
In recent years, deep convolution neural networks (DCNNs) have achieved great prospects in coronary artery vessel segmentation. However, it is difficult to deploy complicated models in clinical scenarios since high-performance approaches have excessive parameters and high computation costs. To tackle this problem, we propose \textbf{LightVessel}, a Similarity Knowledge Distillation Framework, for lightweight coronary artery vessel segmentation. Primarily, we propose a Feature-wise Similarity Distillation (FSD) module for semantic-shift modeling. Specifically, we calculate the feature similarit…
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…
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…
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…
Knowledge distillation facilitates the training of a compact student network by using a deep teacher one. While this has achieved great success in many tasks, it remains completely unstudied for image-based 6D object pose estimation. In this work, we introduce the first knowledge distillation method driven by the 6D pose estimation task. To this end, we observe that most modern 6D pose estimation frameworks output local predictions, such as sparse 2D keypoints or dense representations, and that the compact student network typically struggles to predict such local quantities precisely. Therefor…
The model reduction problem that eases the computation costs and latency of complex deep learning architectures has received an increasing number of investigations owing to its importance in model deployment. One promising method is knowledge distillation (KD), which creates a fast-to-execute student model to mimic a large teacher network. In this paper, we propose a method, called KDFM (Knowledge Distillation with Feature Maps), which improves the effectiveness of KD by learning the feature maps from the teacher network. Two major techniques used in KDFM are shared classifier and generative a…
