Representation knowledge distillation aims at transferring rich information from one model to another. Common approaches for representation distillation mainly focus on the direct minimization of distance metrics between the models' embedding vectors. Such direct methods may be limited in transferring high-order dependencies embedded in the representation vectors, or in handling the capacity gap between the teacher and student models. Moreover, in standard knowledge distillation, the teacher is trained without awareness of the student's characteristics and capacity. In this paper, we explore two mechanisms for enhancing representation distillation using classifier sharing between the teacher and student. We first investigate a simple scheme where the teacher's classifier is connected to the student backbone, acting as an additional classification head. Then, we propose a student-aware mechanism that asks to tailor the teacher model to a student with limited capacity by training the teacher with a temporary student's head. We analyze and compare these two mechanisms and show their effectiveness on various datasets and tasks, including image classification, fine-grained classification, and face verification. In particular, we achieve state-of-the-art results for face verification on the IJB-C dataset for a MobileFaceNet model: TAR@(FAR=1e-5)=93.7\%. Code is available at https://github.com/Alibaba-MIIL/HeadSharingKD.
Head generation with diverse identities is an important task in computer vision and computer graphics, widely used in multimedia applications. However, current full head generation methods require a large number of 3D scans or multi-view images to train the model, resulting in expensive data acquisition cost. To address this issue, we propose Head3D, a method to generate full 3D heads with limited multi-view images. Specifically, our approach first extracts facial priors represented by tri-planes learned in EG3D, a 3D-aware generative model, and then proposes feature distillation to deliver th…
Unsupervised Domain Adaptation (UDA) is a transfer learning task which aims at training on an unlabeled target domain by leveraging a labeled source domain. Beyond the traditional scope of UDA with a single source domain and a single target domain, real-world perception systems face a variety of scenarios to handle, from varying lighting conditions to many cities around the world. In this context, UDAs with several domains increase the challenges with the addition of distribution shifts within the different target domains. This work focuses on a novel framework for learning UDA, continuous UDA…
Krasovskii Institute of Mathematics and Mechanics（克拉斯诺夫斯基数学与力学研究所）；Ural Federal University（乌拉尔联邦大学）
We propose a response-based method of knowledge distillation (KD) for the head pose estimation problem. A student model trained by the proposed KD achieves results better than a teacher model, which is atypical for the response-based method. Our method consists of two stages. In the first stage, we trained the base neural network (NN), which has one regression head and four regression via classification (RvC) heads. We build the convolutional ensemble over the base NN using offsets of face bounding boxes over a regular grid. In the second stage, we perform KD from the convolutional ensemble in…
Sharing medical datasets between hospitals is challenging because of the privacy-protection problem and the massive cost of transmitting and storing many high-resolution medical images. However, dataset distillation can synthesize a small dataset such that models trained on it achieve comparable performance with the original large dataset, which shows potential for solving the existing medical sharing problems. Hence, this paper proposes a novel dataset distillation-based method for medical dataset sharing. Experimental results on a COVID-19 chest X-ray image dataset show that our method can a…
Decentralized learning with private data is a central problem in machine learning. We propose a novel distillation-based decentralized learning technique that allows multiple agents with private non-iid data to learn from each other, without having to share their data, weights or weight updates. Our approach is communication efficient, utilizes an unlabeled public dataset and uses multiple auxiliary heads for each client, greatly improving training efficiency in the case of heterogeneous data. This approach allows individual models to preserve and enhance performance on their private tasks whi…
Feature regression is a simple way to distill large neural network models to smaller ones. We show that with simple changes to the network architecture, regression can outperform more complex state-of-the-art approaches for knowledge distillation from self-supervised models. Surprisingly, the addition of a multi-layer perceptron head to the CNN backbone is beneficial even if used only during distillation and discarded in the downstream task. Deeper non-linear projections can thus be used to accurately mimic the teacher without changing inference architecture and time. Moreover, we utilize inde…
University of Notre Dame（圣母大学）；First Affiliated Hospital of Anhui Medical University（安徽医科大学第一附属医院）
With rising male infertility, sperm head morphology classification becomes critical for accurate and timely clinical diagnosis. Recent deep learning (DL) morphology analysis methods achieve promising benchmark results, but leave performance and robustness on the table by relying on limited and possibly noisy class labels. To address this, we introduce a new DL training framework that leverages anatomical and image priors from human sperm microscopy crops to extract useful features without additional labeling cost. Our core idea is to distill sperm head information with reliably-generated pseud…
Beijing Institute of Technology（北京理工大学）；Wuhan University（武汉大学）；Tsinghua University（清华大学）
Recently, the compression and deployment of powerful deep neural networks (DNNs) on resource-limited edge devices to provide intelligent services have become attractive tasks. Although knowledge distillation (KD) is a feasible solution for compression, its requirement on the original dataset raises privacy concerns. In addition, it is common to integrate multiple pretrained models to achieve satisfactory performance. How to compress multiple models into a tiny model is challenging, especially when the original data are unavailable. To tackle this challenge, we propose a framework termed collab…
University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
In this paper, we present and discuss a deep mixture model with online knowledge distillation (MOD) for large-scale video temporal concept localization, which is ranked 3rd in the 3rd YouTube-8M Video Understanding Challenge. Specifically, we find that by enabling knowledge sharing with online distillation, fintuning a mixture model on a smaller dataset can achieve better evaluation performance. Based on this observation, in our final solution, we trained and fintuned 12 NeXtVLAD models in parallel with a 2-layer online distillation structure. The experimental results show that the proposed di…
The University of Tokyo Hospital（东京大学医院）；Graduate School of Medicine, The University of Tokyo（东京大学医学院）；Junpukai Health Maintenance Center（顺会健康体检中心）；Hokkaido University（北海道大学）
Several methods of knowledge distillation have been developed for neural network compression. While they all use the KL divergence loss to align the soft outputs of the student model more closely with that of the teacher, the various methods differ in how the intermediate features of the student are encouraged to match those of the teacher. In this paper, we propose a simple-to-implement method using auxiliary classifiers at intermediate layers for matching features, which we refer to as multi-head knowledge distillation (MHKD). We add loss terms for training the student that measure the dissi…
Biomechanical 3D Body: Self-Supervised Distillation of Biomechanical Pose from a 3D Body Foundation Model
Shirley Ryan AbilityLab（雪莉·瑞安能力实验室）；Northwestern University（西北大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
The crux of knowledge distillation is to effectively train a resource-limited student model with the guide of a pre-trained larger teacher model. However, when there is a large difference between the model complexities of teacher and student (i.e., capacity gap), knowledge distillation loses its strength in transferring knowledge from the teacher to the student, thus training a weaker student. To mitigate the impact of the capacity gap, we introduce knowledge distillation via intermediate heads. By extending the intermediate layers of the teacher (at various depths) with classifier heads, we c…
Knowledge distillation field delicately designs various types of knowledge to shrink the performance gap between compact student and large-scale teacher. These existing distillation approaches simply focus on the improvement of \textit{knowledge quality}, but ignore the significant influence of \textit{knowledge quantity} on the distillation procedure. Opposed to the conventional distillation approaches, which extract knowledge from a fixed teacher computation graph, this paper explores a non-negligible research direction from a novel perspective of \textit{knowledge quantity} to further impro…
Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an alternative strategy where multiple simple student networks benefit from sharing knowledge, even in the absence of a powerful but static teacher network. Motivated by these findings, we propose a single-teacher, multi-student framework that leverages both KD and ML to achieve better performance. Furthermore, an online distillation strategy is utilized to train the te…
Neural Spectral Decomposition for Dataset Distillation
School of Software Engineering, Xi’an Jiaotong University（西安交通大学软件学院）；Megvii Technology（旷视科技）；University of Electronic Science and Technology of China（电子科技大学）
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…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Nanjing University of Science and Technology（南京理工大学）
Deep models trained on long-tailed datasets exhibit unsatisfactory performance on tail classes. Existing methods usually modify the classification loss to increase the learning focus on tail classes, which unexpectedly sacrifice the performance on head classes. In fact, this scheme leads to a contradiction between the two goals of long-tailed learning, i.e., learning generalizable representations and facilitating learning for tail classes. In this work, we explore knowledge distillation in long-tailed scenarios and propose a novel distillation framework, named Balanced Knowledge Distillation (…
Knowledge distillation usually transfers the knowledge from a pre-trained cumbersome teacher network to a compact student network, which follows the classical teacher-teaching-student paradigm. Based on this paradigm, previous methods mostly focus on how to efficiently train a better student network for deployment. Different from the existing practices, in this paper, we propose a novel student-helping-teacher formula, Teacher Evolution via Self-Knowledge Distillation (TESKD), where the target teacher (for deployment) is learned with the help of multiple hierarchical students by sharing the st…
Beihang University（北京航空航天大学）；SenseTime Research（商汤科技研究院）；ETH Zurich（苏黎世联邦理工学院）；Shandong University（山东大学）；University of Science and Technology of China（中国科学技术大学）
Conventional knowledge distillation (KD) methods for object detection mainly concentrate on homogeneous teacher-student detectors. However, the design of a lightweight detector for deployment is often significantly different from a high-capacity detector. Thus, we investigate KD among heterogeneous teacher-student pairs for a wide application. We observe that the core difficulty for heterogeneous KD (hetero-KD) is the significant semantic gap between the backbone features of heterogeneous detectors due to the different optimization manners. Conventional homogeneous KD (homo-KD) methods suffer …
Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling
School of Artificial Intelligence and Computer Science, Shaanxi Normal University（陕西师范大学人工智能与计算机科学学院）；iFLYTEK Research, iFLYTEK Co., Ltd.（科大讯飞股份有限公司）；Key Laboratory of Intelligent Computing and Service Technology for Folk SongMinistry of Culture and Tourism（文化和旅游部民歌智能计算与服务技术重点实验室）
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；FAIR, Meta AI（Meta人工智能基础研究实验室（FAIR））
Recent advances in egocentric video understanding models are promising, but their heavy computational expense is a barrier for many real-world applications. To address this challenge, we propose EgoDistill, a distillation-based approach that learns to reconstruct heavy egocentric video clip features by combining the semantics from a sparse set of video frames with the head motion from lightweight IMU readings. We further devise a novel self-supervised training strategy for IMU feature learning. Our method leads to significant improvements in efficiency, requiring 200x fewer GFLOPs than equival…
Imperial College London（伦敦帝国理工学院）；The Chinese University of Hong Kong（香港中文大学）
Multi-modal learning is typically performed with network architectures containing modality-specific layers and shared layers, utilizing co-registered images of different modalities. We propose a novel learning scheme for unpaired cross-modality image segmentation, with a highly compact architecture achieving superior segmentation accuracy. In our method, we heavily reuse network parameters, by sharing all convolutional kernels across CT and MRI, and only employ modality-specific internal normalization layers which compute respective statistics. To effectively train such a highly compact model,…
Personalized Federated Learning via Backbone Self-Distillation
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, UCAS（中国科学院大学网络空间安全学院）；School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）；School of Automation, Hangzhou Dianzi University（杭州电子科技大学自动化学院）
Background and objective: Sharing of medical data is required to enable the cross-agency flow of healthcare information and construct high-accuracy computer-aided diagnosis systems. However, the large sizes of medical datasets, the massive amount of memory of saved deep convolutional neural network (DCNN) models, and patients' privacy protection are problems that can lead to inefficient medical data sharing. Therefore, this study proposes a novel soft-label dataset distillation method for medical data sharing. Methods: The proposed method distills valid information of medical image data and ge…
Traditional object detectors are ill-equipped for incremental learning. However, fine-tuning directly on a well-trained detection model with only new data will lead to catastrophic forgetting. Knowledge distillation is a flexible way to mitigate catastrophic forgetting. In Incremental Object Detection (IOD), previous work mainly focuses on distilling for the combination of features and responses. However, they under-explore the information that contains in responses. In this paper, we propose a response-based incremental distillation method, dubbed Elastic Response Distillation (ERD), which fo…
Identity Preserving 3D Head Stylization with Multiview Score Distillation
Bilkent University（比尔肯大学）；ETH Zurich（苏黎世联邦理工学院）；Max Planck Institute（马克斯·普朗克研究所）；INSAIT, Sofia University “St. Kliment Ohridski”（INSAIT，索菲亚大学“圣克莱门特·奥赫里茨基”）
Huazhong University of Science and Technology（华中科技大学）；Wuhan Jingce Electronic Group Co.,Ltd.（武汉精测电子集团股份有限公司）
This paper aims to address the problem of anomaly discovery in semantic segmentation. Our key observation is that semantic classification plays a critical role in existing approaches, while the incorrectly classified pixels are easily regarded as anomalies. Such a phenomenon frequently appears and is rarely discussed, which significantly reduces the performance of anomaly discovery. To this end, we propose a novel Distillation Comparison Network (DiCNet). It comprises of a teacher branch which is a semantic segmentation network that removed the semantic classification head, and a student branc…
Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a larger teacher model, is one of the promising solutions for model miniaturization. In this paper, we investigate each module of a typical detector in depth, and propose a general distillation framework that adaptively transfers knowledge from teacher to student according to the task specific priors. The intuition is that simply distilling all information from …
