Universal style transfer methods typically leverage rich representations from deep Convolutional Neural Network (CNN) models (e.g., VGG-19) pre-trained on large collections of images. Despite the effectiveness, its application is heavily constrained by the large model size to handle ultra-resolution images given limited memory. In this work, we present a new knowledge distillation method (named Collaborative Distillation) for encoder-decoder based neural style transfer to reduce the convolutional filters. The main idea is underpinned by a finding that the encoder-decoder pairs construct an exclusive collaborative relationship, which is regarded as a new kind of knowledge for style transfer models. Moreover, to overcome the feature size mismatch when applying collaborative distillation, a linear embedding loss is introduced to drive the student network to learn a linear embedding of the teacher's features. Extensive experiments show the effectiveness of our method when applied to different universal style transfer approaches (WCT and AdaIN), even if the model size is reduced by 15.5 times. Especially, on WCT with the compressed models, we achieve ultra-resolution (over 40 megapixels) universal style transfer on a 12GB GPU for the first time. Further experiments on optimization-based stylization scheme show the generality of our algorithm on different stylization paradigms. Our code and trained models are available at https://github.com/mingsun-tse/collaborative-distillation.
University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Colorado Boulder（科罗拉多大学博尔德分校）
Photorealistic style transfer entails transferring the style of a reference image to another image so the result seems like a plausible photo. Our work is inspired by the observation that existing models are slow due to their large sizes. We introduce PCA-based knowledge distillation to distill lightweight models and show it is motivated by theory. To our knowledge, this is the first knowledge distillation method for photorealistic style transfer. Our experiments demonstrate its versatility for use with different backbone architectures, VGG and MobileNet, across six image resolutions. Compared…
Jiangsu University（江苏大学）；The University of Sydney（悉尼大学）；Monash University（莫纳什大学）
Knowledge distillation (KD), as an efficient and effective model compression technique, has been receiving considerable attention in deep learning. The key to its success is to transfer knowledge from a large teacher network to a small student one. However, most of the existing knowledge distillation methods consider only one type of knowledge learned from either instance features or instance relations via a specific distillation strategy in teacher-student learning. There are few works that explore the idea of transferring different types of knowledge with different distillation strategies in…
Noah’s Ark Lab, Huawei Technologies（华为技术有限公司诺亚方舟实验室）；University of Sydney（悉尼大学）
Video style transfer techniques inspire many exciting applications on mobile devices. However, their efficiency and stability are still far from satisfactory. To boost the transfer stability across frames, optical flow is widely adopted, despite its high computational complexity, e.g. occupying over 97% inference time. This paper proposes to learn a lightweight video style transfer network via knowledge distillation paradigm. We adopt two teacher networks, one of which takes optical flow during inference while the other does not. The output difference between these two teacher networks highlig…
Yandex；Moscow Institute of Physics and Technology（莫斯科物理技术学院）
StyleGAN2 is a state-of-the-art network in generating realistic images. Besides, it was explicitly trained to have disentangled directions in latent space, which allows efficient image manipulation by varying latent factors. Editing existing images requires embedding a given image into the latent space of StyleGAN2. Latent code optimization via backpropagation is commonly used for qualitative embedding of real world images, although it is prohibitively slow for many applications. We propose a way to distill a particular image manipulation of StyleGAN2 into image-to-image network trained in pai…
Southern University of Science and Technology（南方科技大学）；The University of Hong Kong（香港大学）
Various deep learning models have been developed to segment anatomical structures from medical images, but they typically have poor performance when tested on another target domain with different data distribution. Recently, unsupervised domain adaptation methods have been proposed to alleviate this so-called domain shift issue, but most of them are designed for scenarios with relatively small domain shifts and are likely to fail when encountering a large domain gap. In this paper, we propose DCDA, a novel cross-modality unsupervised domain adaptation framework for tasks with large domain shif…
The Chinese University of Hong Kong（香港中文大学）；Shanghai AI Laboratory（上海人工智能实验室）；Nanyang Technological University（南洋理工大学）
StyleGAN family is one of the most popular Generative Adversarial Networks (GANs) for unconditional generation. Despite its impressive performance, its high demand on storage and computation impedes their deployment on resource-constrained devices. This paper provides a comprehensive study of distilling from the popular StyleGAN-like architecture. Our key insight is that the main challenge of StyleGAN distillation lies in the output discrepancy issue, where the teacher and student model yield different outputs given the same input latent code. Standard knowledge distillation losses typically f…
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…
The latent code of the recent popular model StyleGAN has learned disentangled representations thanks to the multi-layer style-based generator. Embedding a given image back to the latent space of StyleGAN enables wide interesting semantic image editing applications. Although previous works are able to yield impressive inversion results based on an optimization framework, which however suffers from the efficiency issue. In this work, we propose a novel collaborative learning framework that consists of an efficient embedding network and an optimization-based iterator. On one hand, with the progre…
Knowledge distillation (KD) is a well-known method to reduce inference latency by compressing a cumbersome teacher model to a small student model. Despite the success of KD in the classification task, applying KD to recommender models is challenging due to the sparsity of positive feedback, the ambiguity of missing feedback, and the ranking problem associated with the top-N recommendation. To address the issues, we propose a new KD model for the collaborative filtering approach, namely collaborative distillation (CD). Specifically, (1) we reformulate a loss function to deal with the ambiguity …
While noise is commonly considered a nuisance in computing systems, a number of studies in neuroscience have shown several benefits of noise in the nervous system from enabling the brain to carry out computations such as probabilistic inference as well as carrying additional information about the stimuli. Similarly, noise has been shown to improve the performance of deep neural networks. In this study, we further investigate the effect of adding noise in the knowledge distillation framework because of its resemblance to collaborative subnetworks in the brain regions. We empirically show that i…
1 Integrated Graduate School of Medicine, Engineering；Agricultural Sciences, University of Yamanashi, Japan
This paper describes that semi-supervised learning called peer collaborative learning (PCL) can be applied to the polyphonic sound event detection (PSED) task, which is one of the tasks in the Detection and Classification of Acoustic Scenes and Events (DCASE) challenge. Many deep learning models have been studied to find out what kind of sound events occur where and for how long in a given audio clip. The characteristic of PCL used in this paper is the combination of ensemble-based knowledge distillation into sub-networks and student-teacher model-based knowledge distillation, which can train …
Institute of Anthropomatics & Robotics（人类工程学与机器人研究所）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Autonomous Systems（自主系统（部门））；Daimler TSS（戴姆勒TSS）
Generative adversarial networks has emerged as a defacto standard for image translation problems. To successfully drive such models, one has to rely on additional networks e.g., discriminators and/or perceptual networks. Training these networks with pixel based losses alone are generally not sufficient to learn the target distribution. In this paper, we propose a novel method of computing the loss directly between the source and target images that enable proper distillation of shape/content and colour/style. We show that this is useful in typical image-to-image translations allowing us to succ…
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…
Uncertainty-Aware Dual-Student Knowledge Distillation for Efficient Image Classification
Department of Electrical Engineering Indian Institute of Technology Bombay 21D070002（电子工程系 印度理工学院班加罗尔 21D070002）；Department of Electrical Engineering Indian Institute of Technology Bombay 210010010（电子工程系 印度理工学院班加罗尔 210010010）；Department of Electrical Engineering Indian Institute of Technology Bombay 210020023（电子工程系 印度理工学院班加罗尔 210020023）
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…
It is difficult to train classifiers on paintings collections due to model bias from domain gaps and data bias from the uneven distribution of artistic styles. Previous techniques like data distillation, traditional data augmentation and style transfer improve classifier training using task specific training datasets or domain adaptation. We propose a system to handle data bias in small paintings datasets like the Kaokore dataset while simultaneously accounting for domain adaptation in fine-tuning a model trained on real world images. Our system consists of two stages which are style transfer …
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…
In this paper, we propose a framework for predicting frame errors in the collaborative spectrally congested wireless environments of the DARPA Spectrum Collaboration Challenge (SC2) via a recently collected dataset. We employ distributed deep edge learning that is shared among edge nodes and a central cloud. Using this close-to-practice dataset, we find that widely used federated learning approaches, specially those that are privacy preserving, are worse than local training for a wide range of settings. We hence utilize the synthetic minority oversampling technique to maintain privacy via avoi…
Knowledge Distillation in Federated Edge Learning: A Survey
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Zhongguancun Laboratory（中关村实验室）；Beijing Jiaotong University（北京交通大学）
Privacy-preserving machine learning has become a key conundrum for multi-party artificial intelligence. Federated learning (FL) and Split Learning (SL) are two frameworks that enable collaborative learning while keeping the data private (on device). In FL, each data holder trains a model locally and releases it to a central server for aggregation. In SL, the clients must release individual cut-layer activations (smashed data) to the server and wait for its response (during both inference and back propagation). While relevant in several settings, both of these schemes have a high communication …
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）；Sony AI（索尼人工智能研究院）
Federated learning is widely used to learn intelligent models from decentralized data. In federated learning, clients need to communicate their local model updates in each iteration of model learning. However, model updates are large in size if the model contains numerous parameters, and there usually needs many rounds of communication until model converges. Thus, the communication cost in federated learning can be quite heavy. In this paper, we propose a communication efficient federated learning method based on knowledge distillation. Instead of directly communicating the large models betwee…
The robustness of federated learning (FL) is vital for the distributed training of an accurate global model that is shared among large number of clients. The collaborative learning framework by typically aggregating model updates is vulnerable to model poisoning attacks from adversarial clients. Since the shared information between the global server and participants are only limited to model parameters, it is challenging to detect bad model updates. Moreover, real-world datasets are usually heterogeneous and not independent and identically distributed (Non-IID) among participants, which makes …
Although the facial makeup transfer network has achieved high-quality performance in generating perceptually pleasing makeup images, its capability is still restricted by the massive computation and storage of the network architecture. We address this issue by compressing facial makeup transfer networks with collaborative distillation and kernel decomposition. The main idea of collaborative distillation is underpinned by a finding that the encoder-decoder pairs construct an exclusive collaborative relationship, which is regarded as a new kind of knowledge for low-level vision tasks. For kernel…
Tianjin University（天津大学）；Binghamton University, State University of New York（纽约州立大学宾汉姆顿分校）
General Continual Learning (GCL) aims at learning from non independent and identically distributed stream data without catastrophic forgetting of the old tasks that don't rely on task boundaries during both training and testing stages. We reveal that the relation and feature deviations are crucial problems for catastrophic forgetting, in which relation deviation refers to the deficiency of the relationship among all classes in knowledge distillation, and feature deviation refers to indiscriminative feature representations. To this end, we propose a Complementary Calibration (CoCa) framework by…
It is challenging to disentangle an object into two orthogonal spaces of content and style since each can influence the visual observation differently and unpredictably. It is rare for one to have access to a large number of data to help separate the influences. In this paper, we present a novel framework to learn this disentangled representation in a completely unsupervised manner. We address this problem in a two-branch Autoencoder framework. For the structural content branch, we project the latent factor into a soft structured point tensor and constrain it with losses derived from prior kno…
Traditional knowledge distillation uses a two-stage training strategy to transfer knowledge from a high-capacity teacher model to a compact student model, which relies heavily on the pre-trained teacher. Recent online knowledge distillation alleviates this limitation by collaborative learning, mutual learning and online ensembling, following a one-stage end-to-end training fashion. However, collaborative learning and mutual learning fail to construct an online high-capacity teacher, whilst online ensembling ignores the collaboration among branches and its logit summation impedes the further op…
Knowledge distillation which learns a lightweight student model by distilling knowledge from a cumbersome teacher model is an attractive approach for learning compact deep neural networks (DNNs). Recent works further improve student network performance by leveraging multiple teacher networks. However, most of the existing knowledge distillation-based multi-teacher methods use separately pretrained teachers. This limits the collaborative learning between teachers and the mutual learning between teachers and student. Network quantization is another attractive approach for learning compact DNNs. …
