In this paper, we introduce InDistill, a method that serves as a warmup stage for enhancing Knowledge Distillation (KD) effectiveness. InDistill focuses on transferring critical information flow paths from a heavyweight teacher to a lightweight student. This is achieved via a training scheme based on curriculum learning that considers the distillation difficulty of each layer and the critical learning periods when the information flow paths are established. This procedure can lead to a student model that is better prepared to learn from the teacher. To ensure the applicability of InDistill across a wide range of teacher-student pairs, we also incorporate a pruning operation when there is a discrepancy in the width of the teacher and student layers. This pruning operation reduces the width of the teacher's intermediate layers to match those of the student, allowing direct distillation without the need for an encoding stage. The proposed method is extensively evaluated using various pairs of teacher-student architectures on CIFAR-10, CIFAR-100, and ImageNet datasets demonstrating that preserving the information flow paths consistently increases the performance of the baseline KD approaches on both classification and retrieval settings. The code is available at https://github.com/gsarridis/InDistill.
Recent applications pose requirements of both cross-domain knowledge transfer and model compression to machine learning models due to insufficient training data and limited computational resources. In this paper, we propose a new knowledge distillation model, named Spirit Distillation (SD), which is a model compression method with multi-domain knowledge transfer. The compact student network mimics out a representation equivalent to the front part of the teacher network, through which the general knowledge can be transferred from the source domain (teacher) to the target domain (student). To fu…
This paper presents a novel knowledge distillation based model compression framework consisting of a student ensemble. It enables distillation of simultaneously learnt ensemble knowledge onto each of the compressed student models. Each model learns unique representations from the data distribution due to its distinct architecture. This helps the ensemble generalize better by combining every model's knowledge. The distilled students and ensemble teacher are trained simultaneously without requiring any pretrained weights. Moreover, our proposed method can deliver multi-compressed students with s…
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…
Model compression is eminently suited for deploying deep learning on IoT-devices. However, existing model compression techniques rely on access to the original or some alternate dataset. In this paper, we address the model compression problem when no real data is available, e.g., when data is private. To this end, we propose Dream Distillation, a data-independent model compression framework. Our experiments show that Dream Distillation can achieve 88.5% accuracy on the CIFAR-10 test set without actually training on the original data!
Ocean University of China（中国海洋大学）；Technical University of Munich（慕尼黑工业大学）；Virginia Commonwealth University（弗吉尼亚联邦大学）；University of Leicester（莱斯特大学）；University of Portsmouth（朴茨茅斯大学）
Knowledge distillation has been widely used to produce portable and efficient neural networks which can be well applied on edge devices for computer vision tasks. However, almost all top-performing knowledge distillation methods need to access the original training data, which usually has a huge size and is often unavailable. To tackle this problem, we propose a novel data-free approach in this paper, named Dual Discriminator Adversarial Distillation (DDAD) to distill a neural network without any training data or meta-data. To be specific, we use a generator to create samples through dual disc…
In this paper we introduce Principal Filter Analysis (PFA), an easy to use and effective method for neural network compression. PFA exploits the correlation between filter responses within network layers to recommend a smaller network that maintain as much as possible the accuracy of the full model. We propose two algorithms: the first allows users to target compression to specific network property, such as number of trainable variable (footprint), and produces a compressed model that satisfies the requested property while preserving the maximum amount of spectral energy in the responses of ea…
ETH Zurich（苏黎世联邦理工学院）；DisneyResearch|Studios（迪士尼研究院|工作室）
Recently, significant progress has been made in learned image and video compression. In particular the usage of Generative Adversarial Networks has lead to impressive results in the low bit rate regime. However, the model size remains an important issue in current state-of-the-art proposals and existing solutions require significant computation effort on the decoding side. This limits their usage in realistic scenarios and the extension to video compression. In this paper, we demonstrate how to leverage knowledge distillation to obtain equally capable image decoders at a fraction of the origin…
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…
Istituto Italiano di Tecnologia（意大利理工学院）；University of Genova（热那亚大学）；Huawei Technologies Co. Ltd.（华为技术有限公司）；University of Verona（维罗纳大学）
The concept of compressing deep Convolutional Neural Networks (CNNs) is essential to use limited computation, power, and memory resources on embedded devices. However, existing methods achieve this objective at the cost of a drop in inference accuracy in computer vision tasks. To address such a drawback, we propose a framework that leverages knowledge distillation along with customizable block-wise optimization to learn a lightweight CNN structure while preserving better control over the compression-performance tradeoff. Considering specific resource constraints, e.g., floating-point operation…
The performance of a distillation-based compressed network is governed by the quality of distillation. The reason for the suboptimal distillation of a large network (teacher) to a smaller network (student) is largely attributed to the gap in the learning capacities of given teacher-student pair. While it is hard to distill all the knowledge of a teacher, the quality of distillation can be controlled to a large extent to achieve better performance. Our experiments show that the quality of distillation is largely governed by the quality of teacher's response, which in turn is heavily affected by…
Beijing Orion Star Technology Co., Ltd.（北京猎户星空科技有限公司）
Knowledge distillation is a potential solution for model compression. The idea is to make a small student network imitate the target of a large teacher network, then the student network can be competitive to the teacher one. Most previous studies focus on model distillation in the classification task, where they propose different architects and initializations for the student network. However, only the classification task is not enough, and other related tasks such as regression and retrieval are barely considered. To solve the problem, in this paper, we take face recognition as a breaking poi…
LIB-KD: Teaching Inductive Bias for Efficient Vision Transformer Distillation and Compression
Department of Electrical Engineering Indian Institute of Technology Delhi（电子工程系印度理工学院德里）；Yogananda School of AI, Computers and Data Sciences（Yoganananda人工智能、计算机与数据科学学院）
Network pruning is one of the most dominant methods for reducing the heavy inference cost of deep neural networks. Existing methods often iteratively prune networks to attain high compression ratio without incurring significant loss in performance. However, we argue that conventional methods for retraining pruned networks (i.e., using small, fixed learning rate) are inadequate as they completely ignore the benefits from snapshots of iterative pruning. In this work, we show that strong ensembles can be constructed from snapshots of iterative pruning, which achieve competitive performance and va…
AMD: Automatic Multi-step Distillation of Large-scale Vision Models
University of Missouri – Kansas City（密苏里大学堪萨斯分校）；Rochester Institute of Technology（罗切斯特理工学院）；Meta AI；DEVCOM Army Research Laboratory（DEVCOM陆军研究实验室）；Santa Clara University（圣克拉拉大学）；Kent State University（肯特州立大学）；Virginia Tech（弗吉尼亚理工大学）
Knowledge distillation (KD) is commonly deemed as an effective model compression technique in which a compact model (student) is trained under the supervision of a larger pretrained model or an ensemble of models (teacher). Various techniques have been proposed since the original formulation, which mimic different aspects of the teacher such as the representation space, decision boundary, or intra-data relationship. Some methods replace the one-way knowledge distillation from a static teacher with collaborative learning between a cohort of students. Despite the recent advances, a clear underst…
We introduce knowledge distillation for end-to-end person search. End-to-End methods are the current state-of-the-art for person search that solve both detection and re-identification jointly. These approaches for joint optimization show their largest drop in performance due to a sub-optimal detector. We propose two distinct approaches for extra supervision of end-to-end person search methods in a teacher-student setting. The first is adopted from state-of-the-art knowledge distillation in object detection. We employ this to supervise the detector of our person search model at various levels u…
Istanbul Technical University（伊斯坦布尔理工大学）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Arcelik Research and Development（阿奇立克研发中心）
One of the most efficient methods for model compression is hint distillation, where the student model is injected with information (hints) from several different layers of the teacher model. Although the selection of hint points can drastically alter the compression performance, conventional distillation approaches overlook this fact and use the same hint points as in the early studies. Therefore, we propose a clustering based hint selection methodology, where the layers of teacher model are clustered with respect to several metrics and the cluster centers are used as the hint points. Our meth…
Deep convolutional neural network with increased number of parameters has achieved improved precision in task of object detection on natural images, where objects of interests are annotated with horizontal boundary boxes. On aerial images captured from the bird-view perspective, these improvements on model architecture and deeper convolutional layers can also boost the performance on oriented object detection task. However, it is hard to directly apply those state-of-the-art object detectors on the devices with limited computation resources, which necessitates lightweight models through model …
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…
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）
Model compression and knowledge distillation have been successfully applied for cross-architecture and cross-domain transfer learning. However, a key requirement is that training examples are in correspondence across the domains. We show that in many scenarios of practical importance such aligned data can be synthetically generated using computer graphics pipelines allowing domain adaptation through distillation. We apply this technique to learn models for recognizing low-resolution images using labeled high-resolution images, non-localized objects using labeled localized objects, line-drawing…
University of Science and Technology of China（中国科学技术大学）；Tencent AI Lab（腾讯人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）
Correlation filters (CF) have received considerable attention in visual tracking because of their computational efficiency. Leveraging deep features via off-the-shelf CNN models (e.g., VGG), CF trackers achieve state-of-the-art performance while consuming a large number of computing resources. This limits deep CF trackers to be deployed to many mobile platforms on which only a single-core CPU is available. In this paper, we propose to jointly compress and transfer off-the-shelf CNN models within a knowledge distillation framework. We formulate a CNN model pretrained from the image classificati…
Network pruning and knowledge distillation are two widely-known model compression methods that efficiently reduce computation cost and model size. A common problem in both pruning and distillation is to determine compressed architecture, i.e., the exact number of filters per layer and layer configuration, in order to preserve most of the original model capacity. In spite of the great advances in existing works, the determination of an excellent architecture still requires human interference or tremendous experimentations. In this paper, we propose an architecture slimming method that automates…
Despite the success of Deep Learning (DL), the deployment of modern DL models requiring large computational power poses a significant problem for resource-constrained systems. This necessitates building compact networks that reduce computations while preserving performance. Traditional Knowledge Distillation (KD) methods that transfer knowledge from teacher to student (a) use a single-stage and (b) require the whole data set while distilling the knowledge to the student. In this work, we propose a new method called Stagewise Knowledge Distillation (SKD) which builds on traditional KD methods b…
With the improvement of AI chips (e.g., GPU, TPU, and NPU) and the fast development of the Internet of Things (IoT), some robust deep neural networks (DNNs) are usually composed of millions or even hundreds of millions of parameters. Such a large model may not be suitable for directly deploying on low computation and low capacity units (e.g., edge devices). Knowledge distillation (KD) has recently been recognized as a powerful model compression method to decrease the model parameters effectively. The central concept of KD is to extract useful information from the feature maps of a large model …
Spiking Neural Networks (SNN) are energy-efficient computing architectures that exchange spikes for processing information, unlike classical Artificial Neural Networks (ANN). Due to this, SNNs are better suited for real-life deployments. However, similar to ANNs, SNNs also benefit from deeper architectures to obtain improved performance. Furthermore, like the deep ANNs, the memory, compute and power requirements of SNNs also increase with model size, and model compression becomes a necessity. Knowledge distillation is a model compression technique that enables transferring the learning of a la…
Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition
Northwestern Polytechnical University（西北工业大学）；Xijing Hospital, The Fourth Military Medical University（第四军医大学西京医院）；Beijing Technology And Business University（北京工商大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Nankai University（南开大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）
Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；School of Computing, National University of Singapore（新加坡国立大学计算机学院）
With the increasing popularity of deep learning on edge devices, compressing large neural networks to meet the hardware requirements of resource-constrained devices became a significant research direction. Numerous compression methodologies are currently being used to reduce the memory sizes and energy consumption of neural networks. Knowledge distillation (KD) is among such methodologies and it functions by using data samples to transfer the knowledge captured by a large model (teacher) to a smaller one(student). However, due to various reasons, the original training data might not be accessi…
Temporal Saliency-Guided Distillation: A Scalable Framework for Distilling Video Datasets
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（清华大学深圳国际研究生院）；Shanghai Jiao Tong University（上海交通大学）
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Texas A&M University（德州农工大学）；Kwai Inc.（快手公司）
Vision transformers (ViTs) have gained popularity recently. Even without customized image operators such as convolutions, ViTs can yield competitive performance when properly trained on massive data. However, the computational overhead of ViTs remains prohibitive, due to stacking multi-head self-attention modules and else. Compared to the vast literature and prevailing success in compressing convolutional neural networks, the study of Vision Transformer compression has also just emerged, and existing works focused on one or two aspects of compression. This paper proposes a unified ViT compress…
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…
Zhejiang University（浙江大学）；Stevens Institute of Technology（史蒂文斯理工学院）；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院）
Knowledge distillation has demonstrated encouraging performances in deep model compression. Most existing approaches, however, require massive labeled data to accomplish the knowledge transfer, making the model compression a cumbersome and costly process. In this paper, we investigate the practical few-shot knowledge distillation scenario, where we assume only a few samples without human annotations are available for each category. To this end, we introduce a principled dual-stage distillation scheme tailored for few-shot data. In the first step, we graft the student blocks one by one onto 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…
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…
Soft Label Pruning and Quantization for Large-Scale Dataset Distillation
CFAR, Agency for Science, Technology and Research, Singapore（新加坡科技研究局应用科学与技术研究院）；IHPC, Agency for Science, Technology and Research, Singapore（新加坡科技研究局信息与通信技术研究院）；National University of Singapore（新加坡国立大学）
Network quantization is an essential procedure in deep learning for development of efficient fixed-point inference models on mobile or edge platforms. However, as datasets grow larger and privacy regulations become stricter, data sharing for model compression gets more difficult and restricted. In this paper, we consider data-free network quantization with synthetic data. The synthetic data are generated from a generator, while no data are used in training the generator and in quantization. To this end, we propose data-free adversarial knowledge distillation, which minimizes the maximum distan…
The University of Tokyo（东京大学）；National Institute of Informatics（国立信息学研究所）
We push forward neural network compression research by exploiting a novel challenging task of large-scale conditional generative adversarial networks (GANs) compression. To this end, we propose a gradually shrinking GAN (PPCD-GAN) by introducing progressive pruning residual block (PP-Res) and class-aware distillation. The PP-Res is an extension of the conventional residual block where each convolutional layer is followed by a learnable mask layer to progressively prune network parameters as training proceeds. The class-aware distillation, on the other hand, enhances the stability of training b…
Despite excellent performance in image generation, Generative Adversarial Networks (GANs) are notorious for its requirements of enormous storage and intensive computation. As an awesome ''performance maker'', knowledge distillation is demonstrated to be particularly efficacious in exploring low-priced GANs. In this paper, we investigate the irreplaceability of teacher discriminator and present an inventive discriminator-cooperated distillation, abbreviated as DCD, towards refining better feature maps from the generator. In contrast to conventional pixel-to-pixel match methods in feature map di…
