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 single training, which is efficient and flexible for different scenarios. We provide comprehensive experiments using state-of-the-art classification models to validate our framework's effectiveness. Notably, using our framework a 97% compressed ResNet110 student model managed to produce a 10.64% relative accuracy gain over its individual baseline training on CIFAR100 dataset. Similarly a 95% compressed DenseNet-BC(k=12) model managed a 8.17% relative accuracy gain.
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…
Uncertainty-Aware Retinal Vessel Segmentation via Ensemble Distillation
University of Ibadan（伊巴迪安大学）；African Institute for Mathematical Sciences（非洲数学科学研究所）；University College London（伦敦大学学院）；Hertie Institute for Brain Health（海德研究所）
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…
Queen Mary University of London（伦敦玛丽女王大学）；Vision Semantics Ltd（视觉语义有限公司）
Knowledge distillation is effective to train small and generalisable network models for meeting the low-memory and fast running requirements. Existing offline distillation methods rely on a strong pre-trained teacher, which enables favourable knowledge discovery and transfer but requires a complex two-phase training procedure. Online counterparts address this limitation at the price of lacking a highcapacity teacher. In this work, we present an On-the-fly Native Ensemble (ONE) strategy for one-stage online distillation. Specifically, ONE trains only a single multi-branch network while simultan…
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!
The linear ensemble based strategy, i.e., averaging ensemble, has been proposed to improve the performance in unsupervised domain adaptation tasks. However, a typical UDA task is usually challenged by dynamically changing factors, such as variable weather, views, and background in the unlabeled target domain. Most previous ensemble strategies ignore UDA's dynamic and uncontrollable challenge, facing limited feature representations and performance bottlenecks. To enhance the model, adaptability between domains and reduce the computational cost when deploying the ensemble model, we propose a nov…
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…
Hangzhou Dianzi University（杭州电子科技大学）；University of Sydney（悉尼大学）；UBTECH Sydney AI Centre（优必选悉尼人工智能中心）；Australian Centre for Field Robotics（澳大利亚现场机器人研究中心）
Data augmentation has been proved effective in training deep models. Existing data augmentation methods tackle the fine-grained problem by blending image pairs and fusing corresponding labels according to the statistics of mixed pixels, which produces additional noise harmful to the performance of networks. Motivated by this, we present a simple yet effective cross ensemble knowledge distillation (CEKD) model for fine-grained feature learning. We innovatively propose a cross distillation module to provide additional supervision to alleviate the noise problem, and propose a collaborative ensemb…
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…
Manifold theory has been the central concept of many learning methods. However, learning modern CNNs with manifold structures has not raised due attention, mainly because of the inconvenience of imposing manifold structures onto the architecture of the CNNs. In this paper we present ManifoldNet, a novel method to encourage learning of manifold-aware representations. Our approach segments the input manifold into a set of fragments. By assigning the corresponding segmentation id as a pseudo label to every sample, we convert the problem of preserving the local manifold structure into a point-wise…
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…
Traditional knowledge distillation transfers "dark knowledge" of a pre-trained teacher network to a student network, and ignores the knowledge in the training process of the teacher, which we call teacher's experience. However, in realistic educational scenarios, learning experience is often more important than learning results. In this work, we propose a novel knowledge distillation method by integrating the teacher's experience for knowledge transfer, named experience ensemble knowledge distillation (EEKD). We save a moderate number of intermediate models from the training process of the tea…
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…
This paper proposes a novel knowledge distillation-based learning method to improve the classification performance of convolutional neural networks (CNNs) without a pre-trained teacher network, called exit-ensemble distillation. Our method exploits the multi-exit architecture that adds auxiliary classifiers (called exits) in the middle of a conventional CNN, through which early inference results can be obtained. The idea of our method is to train the network using the ensemble of the exits as the distillation target, which greatly improves the classification performance of the overall network.…
Recent researches on unsupervised domain adaptation (UDA) have demonstrated that end-to-end ensemble learning frameworks serve as a compelling option for UDA tasks. Nevertheless, these end-to-end ensemble learning methods often lack flexibility as any modification to the ensemble requires retraining of their frameworks. To address this problem, we propose a flexible ensemble-distillation framework for performing semantic segmentation based UDA, allowing any arbitrary composition of the members in the ensemble while still maintaining its superior performance. To achieve such flexibility, our fr…
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…
Ensemble models comprising of deep Convolutional Neural Networks (CNN) have shown significant improvements in model generalization but at the cost of large computation and memory requirements. In this paper, we present a framework for learning compact CNN models with improved classification performance and model generalization. For this, we propose a CNN architecture of a compact student model with parallel branches which are trained using ground truth labels and information from high capacity teacher networks in an ensemble learning fashion. Our framework provides two main benefits: i) Distil…
Graduate School of Convergence Science and Technology（融合科学与技术研究生院）；Seoul National University（首尔国立大学）
Knowledge Distillation (KD) aims to transfer knowledge in a teacher-student framework, by providing the predictions of the teacher network to the student network in the training stage to help the student network generalize better. It can use either a teacher with high capacity or {an} ensemble of multiple teachers. However, the latter is not convenient when one wants to use feature-map-based distillation methods. For a solution, this paper proposes a versatile and powerful training algorithm named FEature-level Ensemble for knowledge Distillation (FEED), which aims to transfer the ensemble kno…
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…
The University of Queensland（昆士兰大学）；CSIRO Data61（澳大利亚联邦科学与工业研究组织Data61部门）
In knowledge distillation, previous feature distillation methods mainly focus on the design of loss functions and the selection of the distilled layers, while the effect of the feature projector between the student and the teacher remains under-explored. In this paper, we first discuss a plausible mechanism of the projector with empirical evidence and then propose a new feature distillation method based on a projector ensemble for further performance improvement. We observe that the student network benefits from a projector even if the feature dimensions of the student and the teacher are the …
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…
University at Buffalo（布法罗大学）；United Imaging Intelligence（联影智能）
Federated Learning (FL) is a machine learning paradigm where local nodes collaboratively train a central model while the training data remains decentralized. Existing FL methods typically share model parameters or employ co-distillation to address the issue of unbalanced data distribution. However, they suffer from communication bottlenecks. More importantly, they risk privacy leakage. In this work, we develop a privacy preserving and communication efficient method in a FL framework with one-shot offline knowledge distillation using unlabeled, cross-domain public data. We propose a quantized a…
Remote sensing (RS) image scene classification task faces many challenges due to the interference from different characteristics of different geographical elements. To solve this problem, we propose a multi-branch ensemble network to enhance the feature representation ability by fusing features in final output logits and intermediate feature maps. However, simply adding branches will increase the complexity of models and decline the inference efficiency. On this issue, we embed self-distillation (SD) method to transfer knowledge from ensemble network to main-branch in it. Through optimizing wi…
Domain generalization is the task of learning models that generalize to unseen target domains. We propose a simple yet effective method for domain generalization, named cross-domain ensemble distillation (XDED), that learns domain-invariant features while encouraging the model to converge to flat minima, which recently turned out to be a sufficient condition for domain generalization. To this end, our method generates an ensemble of the output logits from training data with the same label but from different domains and then penalizes each output for the mismatch with the ensemble. Also, we pre…
Bayesian models have many desirable properties, most notable is their ability to generalize from limited data and to properly estimate the uncertainty in their predictions. However, these benefits come at a steep computational cost as Bayesian inference, in most cases, is computationally intractable. One popular approach to alleviate this problem is using a Monte-Carlo estimation with an ensemble of models sampled from the posterior. However, this approach still comes at a significant computational cost, as one needs to store and run multiple models at test time. In this work, we investigate h…
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…
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…
Generative Adversarial Networks (GANs) have witnessed prevailing success in yielding outstanding images, however, they are burdensome to deploy on resource-constrained devices due to ponderous computational costs and hulking memory usage. Although recent efforts on compressing GANs have acquired remarkable results, they still exist potential model redundancies and can be further compressed. To solve this issue, we propose a novel online multi-granularity distillation (OMGD) scheme to obtain lightweight GANs, which contributes to generating high-fidelity images with low computational demands. W…
Generative adversarial networks (GANs), e.g., StyleGAN2, play a vital role in various image generation and synthesis tasks, yet their notoriously high computational cost hinders their efficient deployment on edge devices. Directly applying generic compression approaches yields poor results on GANs, which motivates a number of recent GAN compression works. While prior works mainly accelerate conditional GANs, e.g., pix2pix and CycleGAN, compressing state-of-the-art unconditional GANs has rarely been explored and is more challenging. In this paper, we propose novel approaches for unconditional G…
Beijing Jiaotong University（北京交通大学）；Institute of Information Science（信息科学研究所）；Beijing Key Laboratory of Advanced Information Science and Network Technology（北京先进信息科学与网络技术重点实验室）
Recently, horizontal representation-based panoramic semantic segmentation approaches outperform projection-based solutions, because the distortions can be effectively removed by compressing the spherical data in the vertical direction. However, these methods ignore the distortion distribution prior and are limited to unbalanced receptive fields, e.g., the receptive fields are sufficient in the vertical direction and insufficient in the horizontal direction. Differently, a vertical representation compressed in another direction can offer implicit distortion prior and enlarge horizontal receptiv…
Ensembling is a universally useful approach to boost the performance of machine learning models. However, individual models in an ensemble were traditionally trained independently in separate stages without information access about the overall ensemble. Many co-distillation approaches were proposed in order to treat model ensembling as first-class citizens. In this paper, we reveal a deeper connection between ensembling and distillation, and come up with a simpler yet more effective co-distillation architecture. On large-scale datasets including ImageNet, YouTube-8M, and Kinetics, we demonstra…
Panasonic R&D Center Singapore（松下新加坡研发中心）；National University of Singapore（新加坡国立大学）
Fully convolutional networks (FCNs) have become de facto tool to achieve very high-level performance for many vision and non-vision tasks in general and face recognition in particular. Such high-level accuracies are normally obtained by very deep networks or their ensemble. However, deploying such high performing models to resource constraint devices or real-time applications is challenging. In this paper, we present a novel model compression approach based on student-teacher paradigm for face recognition applications. The proposed approach consists of training teacher FCN at bigger image reso…
SZABIST（巴基斯坦真纳科技大学）；Technische Universität Dresden (TU Dresden)（德累斯顿工业大学）
Facial expressions are the most common universal forms of body language. In the past few years, automatic facial expression recognition (FER) has been an active field of research. However, it is still a challenging task due to different uncertainties and complications. Nevertheless, efficiency and performance are yet essential aspects for building robust systems. We proposed two models, EmoXNet which is an ensemble learning technique for learning convoluted facial representations, and EmoXNetLite which is a distillation technique that is useful for transferring the knowledge from our ensemble …
Efficient Multi-modal Large Language Models via Progressive Consistency Distillation
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；Duke University（杜克大学）；The University of Hong Kong（香港大学）；Peking University（北京大学）；University of Chicago（芝加哥大学）；Sun Yat-sen University（中山大学）
Flordia International University（佛罗里达国际大学）；Northeastern University（东北大学）
Image compression-based approaches for defending against the adversarial-example attacks, which threaten the safety use of deep neural networks (DNN), have been investigated recently. However, prior works mainly rely on directly tuning parameters like compression rate, to blindly reduce image features, thereby lacking guarantee on both defense efficiency (i.e. accuracy of polluted images) and classification accuracy of benign images, after applying defense methods. To overcome these limitations, we propose a JPEG-based defensive compression framework, namely "feature distillation", to effectiv…
