There is an increasing interest on accelerating neural networks for real-time applications. We study the student-teacher strategy, in which a small and fast student network is trained with the auxiliary information learned from a large and accurate teacher network. We propose to use conditional adversarial networks to learn the loss function to transfer knowledge from teacher to student. The proposed method is particularly effective for relatively small student networks. Moreover, experimental results show the effect of network size when the modern networks are used as student. We empirically study the trade-off between inference time and classification accuracy, and provide suggestions on choosing a proper student network.
Zhejiang University（浙江大学）；Hangzhou City University（浙大城市学院）；ZJU-Bangsun Joint Research Center（浙江大学-邦盛联合研究中心）；Shanghai Institute for Advanced Study of Zhejiang University（浙江大学上海高等研究院）
We introduce latency-aware network acceleration (LANA) - an approach that builds on neural architecture search techniques and teacher-student distillation to accelerate neural networks. LANA consists of two phases: in the first phase, it trains many alternative operations for every layer of the teacher network using layer-wise feature map distillation. In the second phase, it solves the combinatorial selection of efficient operations using a novel constrained integer linear optimization (ILP) approach. ILP brings unique properties as it (i) performs NAS within a few seconds to minutes, (ii) ea…
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）
National University of Defense Technology（国防科技大学）；Chinese Academy of Sciences（中国科学院）
Knowledge distillation (KD) is an effective training strategy to improve the lightweight student models under the guidance of cumbersome teachers. However, the large architecture difference across the teacher-student pairs limits the distillation gains. In contrast to previous adaptive distillation methods to reduce the teacher-student gap, we explore a novel training-free framework to search for the best student architectures for a given teacher. Our work first empirically show that the optimal model under vanilla training cannot be the winner in distillation. Secondly, we find that the simil…
Sun Yat-Sen University（中山大学）；University of Alberta（阿尔伯塔大学）
Knowledge distillation is an effective technique that transfers knowledge from a large teacher model to a shallow student. However, just like massive classification, large scale knowledge distillation also imposes heavy computational costs on training models of deep neural networks, as the softmax activations at the last layer involve computing probabilities over numerous classes. In this work, we apply the idea of importance sampling which is often used in Neural Machine Translation on large scale knowledge distillation. We present a method called dynamic importance sampling, where ranked cla…
Indian Institute of Technology, Jodhpur（焦特布尔印度理工学院）
Knowledge distillation is a common technique for improving the performance of a shallow student network by transferring information from a teacher network, which in general, is comparatively large and deep. These teacher networks are pre-trained and often uncalibrated, as no calibration technique is applied to the teacher model while training. Calibration of a network measures the probability of correctness for any of its predictions, which is critical in high-risk domains. In this paper, we study how to obtain a calibrated student from an uncalibrated teacher. Our approach relies on the fusio…
Xiamen University（厦门大学）；Tencent（腾讯）；Pinterest；Peking University（北京大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Existing online knowledge distillation approaches either adopt the student with the best performance or construct an ensemble model for better holistic performance. However, the former strategy ignores other students' information, while the latter increases the computational complexity during deployment. In this paper, we propose a novel method for online knowledge distillation, termed FFSD, which comprises two key components: Feature Fusion and Self-Distillation, towards solving the above problems in a unified framework. Different from previous works, where all students are treated equally, t…
The University of Sydney（悉尼大学）；Birkbeck College, University of London（伦敦大学伯贝克学院）；UBTECH（优必选）
In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. The great success of deep learning is mainly due to its scalability to encode large-scale data and to maneuver billions of model parameters. However, it is a challenge to deploy these cumbersome deep models on devices with limited resources, e.g., mobile phones and embedded devices, not only because of the high computational complexity but also the large storage requirements. To this end, a variety of model compression and acceleration techniques have been developed. …
Deep learning networks are being developed in every stage of the MRI workflow and have provided state-of-the-art results. However, this has come at the cost of increased computation requirement and storage. Hence, replacing the networks with compact models at various stages in the MRI workflow can significantly reduce the required storage space and provide considerable speedup. In computer vision, knowledge distillation is a commonly used method for model compression. In our work, we propose a knowledge distillation (KD) framework for the image to image problems in the MRI workflow in order to…
Cross Architecture Distillation for 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）；University of Chinese Academy of Sciences（中国科学院大学）；China Telecom Corporation Ltd. Data & AI Technology Company（中国电信股份有限公司数据与AI科技公司）；Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院）
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Beijing University of Posts and Telecommunications（北京邮电大学）；Tencent（腾讯）
With the growth of high-dimensional sparse data in web-scale recommender systems, the computational cost to learn high-order feature interaction in CTR prediction task largely increases, which limits the use of high-order interaction models in real industrial applications. Some recent knowledge distillation based methods transfer knowledge from complex teacher models to shallow student models for accelerating the online model inference. However, they suffer from the degradation of model accuracy in knowledge distillation process. It is challenging to balance the efficiency and effectiveness of…
Tianjin University（天津大学）；The Chinese University of Hong Kong（香港中文大学）；SenseTime Group Limited（商汤科技集团有限公司）；Nanyang Technological University（南洋理工大学）
Knowledge distillation (KD) is one of the most potent ways for model compression. The key idea is to transfer the knowledge from a deep teacher model (T) to a shallower student (S). However, existing methods suffer from performance degradation due to the substantial gap between the learning capacities of S and T. To remedy this problem, this work proposes Residual Knowledge Distillation (RKD), which further distills the knowledge by introducing an assistant (A). Specifically, S is trained to mimic the feature maps of T, and A aids this process by learning the residual error between them. In th…
Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers
University of Bucharest（布加勒斯特大学）；Norwegian University of Science and Technology（挪威科技大学）；University of Medicine and Pharmacy “Carol Davila”（卡罗尔·达维拉医药大学）
Knowledge Distillation (KD) has been considered as a key solution in model compression and acceleration in recent years. In KD, a small student model is generally trained from a large teacher model by minimizing the divergence between the probabilistic outputs of the two. However, as demonstrated in our experiments, existing KD methods might not transfer critical explainable knowledge of the teacher to the student, i.e. the explanations of predictions made by the two models are not consistent. In this paper, we propose a novel explainable knowledge distillation model, called XDistillation, thr…
Deep neural networks have achieved increasingly accurate results on a wide variety of complex tasks. However, much of this improvement is due to the growing use and availability of computational resources (e.g use of GPUs, more layers, more parameters, etc). Most state-of-the-art deep networks, despite performing well, over-parameterize approximate functions and take a significant amount of time to train. With increased focus on deploying deep neural networks on resource constrained devices like smart phones, there has been a push to evaluate why these models are so resource hungry and how the…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Snap Inc.（色拉布公司）
Graph Neural Networks (GNNs) are popular for graph machine learning and have shown great results on wide node classification tasks. Yet, they are less popular for practical deployments in the industry owing to their scalability challenges incurred by data dependency. Namely, GNN inference depends on neighbor nodes multiple hops away from the target, and fetching them burdens latency-constrained applications. Existing inference acceleration methods like pruning and quantization can speed up GNNs by reducing Multiplication-and-ACcumulation (MAC) operations, but the improvements are limited given…
University of California, Los Angeles（加州大学洛杉矶分校）；Tsinghua University（清华大学）
Knowledge Distillation (KD) has been one of the most popu-lar methods to learn a compact model. However, it still suffers from highdemand in time and computational resources caused by sequential train-ing pipeline. Furthermore, the soft targets from deeper models do notoften serve as good cues for the shallower models due to the gap of com-patibility. In this work, we consider these two problems at the same time.Specifically, we propose that better soft targets with higher compatibil-ity can be generated by using a label generator to fuse the feature mapsfrom deeper stages in a top-down manner…
In recent years, deep learning has spread rapidly, and deeper, larger models have been proposed. However, the calculation cost becomes enormous as the size of the models becomes larger. Various techniques for compressing the size of the models have been proposed to improve performance while reducing computational costs. One of the methods to compress the size of the models is knowledge distillation (KD). Knowledge distillation is a technique for transferring knowledge of deep or ensemble models with many parameters (teacher model) to smaller shallow models (student model). Since the purpose of…
Microsoft Dynamics 365 AI Research（微软Dynamics 365人工智能研究院）
Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application in practice. In order to alleviate this resource hunger in large-scale model training, we propose a Patient Knowledge Distillation approach to compress an original large model (teacher) into an equally-effective lightweight shallow network (student). Different from previous knowledge distillation methods, which only use the output from the last layer of the teacher network for …
Deep and large pre-trained language models are the state-of-the-art for various natural language processing tasks. However, the huge size of these models could be a deterrent to use them in practice. Some recent and concurrent works use knowledge distillation to compress these huge models into shallow ones. In this work we study knowledge distillation with a focus on multi-lingual Named Entity Recognition (NER). In particular, we study several distillation strategies and propose a stage-wise optimization scheme leveraging teacher internal representations that is agnostic of teacher architectur…
Knowledge distillation (KD) is a successful approach for deep neural network acceleration, with which a compact network (student) is trained by mimicking the softmax output of a pre-trained high-capacity network (teacher). In tradition, KD usually relies on access to the training samples and the parameters of the white-box teacher to acquire the transferred knowledge. However, these prerequisites are not always realistic due to storage costs or privacy issues in real-world applications. Here we propose the concept of decision-based black-box (DB3) knowledge distillation, with which the student…
In recent years the empirical success of transfer learning with neural networks has stimulated an increasing interest in obtaining a theoretical understanding of its core properties. Knowledge distillation where a smaller neural network is trained using the outputs of a larger neural network is a particularly interesting case of transfer learning. In the present work, we introduce a statistical physics framework that allows an analytic characterization of the properties of knowledge distillation (KD) in shallow neural networks. Focusing the analysis on a solvable model that exhibits a non-triv…
Vast requirement of computation power of Deep Neural Networks is a major hurdle to their real world applications. Many recent Application Specific Integrated Circuit (ASIC) chips feature dedicated hardware support for Neural Network Acceleration. However, as ASICs take multiple years to develop, they are inevitably out-paced by the latest development in Neural Architecture Research. For example, Transformer Networks do not have native support on many popular chips, and hence are difficult to deploy. In this paper, we propose Arch-Net, a family of Neural Networks made up of only operators effic…
Convolutional neural networks have been widely deployed in various application scenarios. In order to extend the applications' boundaries to some accuracy-crucial domains, researchers have been investigating approaches to boost accuracy through either deeper or wider network structures, which brings with them the exponential increment of the computational and storage cost, delaying the responding time. In this paper, we propose a general training framework named self distillation, which notably enhances the performance (accuracy) of convolutional neural networks through shrinking the size of t…
Uncertainty-Aware Multi-Expert Knowledge Distillation for Imbalanced Disease Grading
School of Public Health, Zhejiang University（浙江大学公共卫生学院）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Liangzhu Laboratory and WeDoctor Cloud（良渚实验室和WeDoctor云）；State Key Laboratory of Transvascular Implantation Devices, The Second Affiliated Hospital Zhejiang University School of Medicine（浙江大学医学院第二附属医院心血管植入器械国家重点实验室）；Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence（浙江省医学影像人工智能重点实验室）；School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）
Optimizing Few-Step Generation with Adaptive Matching Distillation
xLeaF Lab, The Hong Kong University of Science（xLeaF实验室，香港科学与技术大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学，深圳）；School of Intelligence Science（智能科学学院）
Zhejiang University（浙江大学）；National University of Singapore（新加坡国立大学）；Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究中心）
Data-free knowledge distillation (DFKD) has recently been attracting increasing attention from research communities, attributed to its capability to compress a model only using synthetic data. Despite the encouraging results achieved, state-of-the-art DFKD methods still suffer from the inefficiency of data synthesis, making the data-free training process extremely time-consuming and thus inapplicable for large-scale tasks. In this work, we introduce an efficacious scheme, termed as FastDFKD, that allows us to accelerate DFKD by a factor of orders of magnitude. At the heart of our approach is a…
Elucidating the Preconditioning in Consistency Distillation
Dept. of Comp. Sci. & Tech., Institute for AI, BNRist Center, THBI Lab（计算机科学与技术系，人工智能研究所，BNRist中心，THBI实验室）；Tsinghua-Bosch Joint ML Center, Tsinghua University（清华大学-博世联合机器学习中心，清华大学）；Shengshu Technology（盛舒科技）；Pazhou Lab (Huangpu), Guangzhou, China（黄埔实验室（广州），中国）
Multimodal Fake News Detection: MFND Dataset and Shallow-Deep Multitask Learning
School of Artificial Intelligence, Hebei University of Technology（河北工业大学人工智能学院）；School of Computing and Information Technology, Great Bay University（大湾大学计算与信息学院）；Guangdong Provincial Key Laboratory of Intelligent Information Processing & Shenzhen Key Laboratory of Media Security, Shenzhen University（广东省智能信息处理重点实验室 & 深圳市媒体安全重点实验室）；Dongguan Key Laboratory for Intelligence and Information Technology（东莞智能信息科技重点实验室）
Nagoya University（名古屋大学）；Navier, Inc.（Navier公司）；The University of Tokyo（东京大学）；Ritsumeikan University（立命馆大学）；Hitotsubashi University（一桥大学）
The number of traffic accidents has been continuously increasing in recent years worldwide. Many accidents are caused by distracted drivers, who take their attention away from driving. Motivated by the success of Convolutional Neural Networks (CNNs) in computer vision, many researchers developed CNN-based algorithms to recognize distracted driving from a dashcam and warn the driver against unsafe behaviors. However, current models have too many parameters, which is unfeasible for vehicle-mounted computing. This work proposes a novel knowledge-distillation-based framework to solve this problem.…
Beihang University（北京航空航天大学）；iQIYI, Inc（爱奇艺公司）；Peking University（北京大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）
Large convolutional neural network models have recently demonstrated impressive performance on video attention prediction. Conventionally, these models are with intensive computation and large memory. To address these issues, we design an extremely light-weight network with ultrafast speed, named UVA-Net. The network is constructed based on depth-wise convolutions and takes low-resolution images as input. However, this straight-forward acceleration method will decrease performance dramatically. To this end, we propose a coupled knowledge distillation strategy to augment and train the network e…
Xiamen University（厦门大学）；National University of Singapore（新加坡国立大学）
The large memory and computation consumption in convolutional neural networks (CNNs) has been one of the main barriers for deploying them on resource-limited systems. To this end, most cheap convolutions (e.g., group convolution, depth-wise convolution, and shift convolution) have recently been used for memory and computation reduction but with the specific architecture designing. Furthermore, it results in a low discriminability of the compressed networks by directly replacing the standard convolution with these cheap ones. In this paper, we propose to use knowledge distillation to improve th…
Anhui University（安徽大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Qiyuan Laboratory（启源实验室）；Tsinghua University（清华大学）
In this paper, we propose a novel self-distillation method for fake speech detection (FSD), which can significantly improve the performance of FSD without increasing the model complexity. For FSD, some fine-grained information is very important, such as spectrogram defects, mute segments, and so on, which are often perceived by shallow networks. However, shallow networks have much noise, which can not capture this very well. To address this problem, we propose using the deepest network instruct shallow network for enhancing shallow networks. Specifically, the networks of FSD are divided into s…
ShaRP: SHAllow-LayeR Pruning for Efficient Video Large Language Models
VCIP & TMCC & DISSec, College of Computer Science, Nankai University（VCIP与TMCC与DISSec学院，南开大学计算机科学学院）；LIX, Ecole Polytechnique, IP Paris（LIX，巴黎高等理工学院，IP巴黎）；OPPO Research Institute（OPPO研究院）；Beijing University of Posts and Telecommunications（北京邮电大学）
Nanjing University of Science and Technology（南京理工大学）；Sensetime Research（商汤科技研究院）
Knowledge Distillation (KD) is a widely-used technology to inherit information from cumbersome teacher models to compact student models, consequently realizing model compression and acceleration. Compared with image classification, object detection is a more complex task, and designing specific KD methods for object detection is non-trivial. In this work, we elaborately study the behaviour difference between the teacher and student detection models, and obtain two intriguing observations: First, the teacher and student rank their detected candidate boxes quite differently, which results in the…
With numerous medical tasks, the performance of deep models has recently experienced considerable improvements. These models are often adept learners. Yet, their intricate architectural design and high computational complexity make deploying them in clinical settings challenging, particularly with devices with limited resources. To deal with this issue, Knowledge Distillation (KD) has been proposed as a compression method and an acceleration technology. KD is an efficient learning strategy that can transfer knowledge from a burdensome model (i.e., teacher model) to a lightweight model (i.e., s…
