Knowledge Distillation (KD) is a common method for transferring the ``knowledge'' learned by one machine learning model (the \textit{teacher}) into another model (the \textit{student}), where typically, the teacher has a greater capacity (e.g., more parameters or higher bit-widths). To our knowledge, existing methods overlook the fact that although the student absorbs extra knowledge from the teacher, both models share the same input data -- and this data is the only medium by which the teacher's knowledge can be demonstrated. Due to the difference in model capacities, the student may not benefit fully from the same data points on which the teacher is trained. On the other hand, a human teacher may demonstrate a piece of knowledge with individualized examples adapted to a particular student, for instance, in terms of her cultural background and interests. Inspired by this behavior, we design data augmentation agents with distinct roles to facilitate knowledge distillation. Our data augmentation agents generate distinct training data for the teacher and student, respectively. We find empirically that specially tailored data points enable the teacher's knowledge to be demonstrated more effectively to the student. We compare our approach with existing KD methods on training popular neural architectures and demonstrate that role-wise data augmentation improves the effectiveness of KD over strong prior approaches. The code for reproducing our results can be found at https://github.com/bigaidream-projects/role-kd
University of Science and Technology of China（中国科学技术大学）；Sun Yat-sen University（中山大学）
Knowledge distillation is to transfer the knowledge from the data learned by the teacher network to the student network, so that the student has the advantage of less parameters and less calculations, and the accuracy is close to the teacher. In this paper, we propose a new distillation method, which contains two transfer distillation strategies and a loss decay strategy. The first transfer strategy is based on channel-wise attention, called Channel Distillation (CD). CD transfers the channel information from the teacher to the student. The second is Guided Knowledge Distillation (GKD). Unlike…
Generalization Performance of Deep Learning models trained using Empirical Risk Minimization can be improved significantly by using Data Augmentation strategies such as simple transformations, or using Mixed Samples. We attempt to empirically analyze the impact of such strategies on the transfer of generalization between teacher and student models in a distillation setup. We observe that if a teacher is trained using any of the mixed sample augmentation strategies, such as MixUp or CutMix, the student model distilled from it is impaired in its generalization capabilities. We hypothesize that s…
Knowledge distillation (KD) is a general neural network training approach that uses a teacher model to guide the student model. Existing works mainly study KD from the network output side (e.g., trying to design a better KD loss function), while few have attempted to understand it from the input side. Especially, its interplay with data augmentation (DA) has not been well understood. In this paper, we ask: Why do some DA schemes (e.g., CutMix) inherently perform much better than others in KD? What makes a "good" DA in KD? Our investigation from a statistical perspective suggests that a good DA…
Korea Advanced Institute of Science and Technology（韩国科学技术院）；University of California, Berkeley（加州大学伯克利分校）
Deep neural networks with millions of parameters may suffer from poor generalization due to overfitting. To mitigate the issue, we propose a new regularization method that penalizes the predictive distribution between similar samples. In particular, we distill the predictive distribution between different samples of the same label during training. This results in regularizing the dark knowledge (i.e., the knowledge on wrong predictions) of a single network (i.e., a self-knowledge distillation) by forcing it to produce more meaningful and consistent predictions in a class-wise manner. Consequen…
Shanghai University of Finance and Economics（上海财经大学）
Knowledge distillation uses both real hard labels and soft labels predicted by teacher models as supervision. Intuitively, we expect the soft labels and hard labels to be concordant w.r.t. their orders of probabilities. However, we found critical order violations between hard labels and soft labels in augmented samples. For example, for an augmented sample $x=0.7*panda+0.3*cat$, we expect the order of meaningful soft labels to be $P_\text{soft}(panda|x)>P_\text{soft}(cat|x)>P_\text{soft}(other|x)$. But real soft labels usually violate the order, e.g. $P_\text{soft}(tiger|x)>P_\text{soft}(panda…
Arizona State University（亚利桑那州立大学）；SRI International（斯坦福国际研究院）
Deep neural networks are parametrized by several thousands or millions of parameters, and have shown tremendous success in many classification problems. However, the large number of parameters makes it difficult to integrate these models into edge devices such as smartphones and wearable devices. To address this problem, knowledge distillation (KD) has been widely employed, that uses a pre-trained high capacity network to train a much smaller network, suitable for edge devices. In this paper, for the first time, we study the applicability and challenges of using KD for time-series data for wea…
University of Alabama in Huntsville（阿拉巴马大学亨茨维尔分校）；Columbia University（哥伦比亚大学）
Detecting anomalies has become increasingly critical to the financial service industry. Anomalous events are often indicative of illegal activities such as fraud, identity theft, network intrusion, account takeover, and money laundering. Financial anomaly detection use cases face serious challenges due to the dynamic nature of the underlying patterns especially in adversarial environments such as constantly changing fraud tactics. While retraining the models with the new patterns is absolutely essential; keeping up with the rapid changes introduces other challenges as it moves the model away f…
Learning Accurate, Efficient, and Interpretable MLPs on Multiplex Graphs via Node-wise Multi-View Ensemble Distillation
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；Laboratory for Big Data and Decision, National University of Defense Technology（国防科技大学大数据与决策实验室）
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…
SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）；Centre for Perceptual and Interactive Intelligence（感知与交互智能研究中心）
Recent studies pointed out that knowledge distillation (KD) suffers from two degradation problems, the teacher-student gap and the incompatibility with strong data augmentations, making it not applicable to training state-of-the-art models, which are trained with advanced augmentations. However, we observe that a key factor, i.e., the temperatures in the softmax functions for generating probabilities of both the teacher and student models, was mostly overlooked in previous methods. With properly tuned temperatures, such degradation problems of KD can be much mitigated. However, instead of rely…
Knowledge distillation aims at transferring knowledge acquired in one model (a teacher) to another model (a student) that is typically smaller. Previous approaches can be expressed as a form of training the student to mimic output activations of individual data examples represented by the teacher. We introduce a novel approach, dubbed relational knowledge distillation (RKD), that transfers mutual relations of data examples instead. For concrete realizations of RKD, we propose distance-wise and angle-wise distillation losses that penalize structural differences in relations. Experiments conduct…
Decoupling Dark Knowledge via Block-wise Logit Distillation for Feature-level Alignment
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息与电子工程学院）；ZJU-UIUC Institute, Zhejiang University（浙江大学-伊利诺伊大学厄巴纳-香槟分校联合学院）
We survey various knowledge distillation (KD) strategies for simple classification tasks and implement a set of techniques that claim state-of-the-art accuracy. Our experiments using standardized model architectures, fixed compute budgets, and consistent training schedules indicate that many of these distillation results are hard to reproduce. This is especially apparent with methods using some form of feature distillation. Further examination reveals a lack of generalizability where these techniques may only succeed for specific architectures and training settings. We observe that appropriate…
Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；University of Waterloo（滑铁卢大学）
Data Augmentation (DA) is known to improve the generalizability of deep neural networks. Most existing DA techniques naively add a certain number of augmented samples without considering the quality and the added computational cost of these samples. To tackle this problem, a common strategy, adopted by several state-of-the-art DA methods, is to adaptively generate or re-weight augmented samples with respect to the task objective during training. However, these adaptive DA methods: (1) are computationally expensive and not sample-efficient, and (2) are designed merely for a specific setting. In…
Horizon Robotics（地平线机器人）；University at Buffalo（布法罗大学）；Tsinghua University（清华大学）
Knowledge distillation is an effective approach to leverage a well-trained network or an ensemble of them, named as the teacher, to guide the training of a student network. The outputs from the teacher network are used as soft labels for supervising the training of a new network. Recent studies \citep{muller2019does,yuan2020revisiting} revealed an intriguing property of the soft labels that making labels soft serves as a good regularization to the student network. From the perspective of statistical learning, regularization aims to reduce the variance, however how bias and variance change is n…
HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
KAIST（韩国科学技术院）；Theori；Université de Montréal（蒙特利尔大学）；Mila – Québec AI Institute（米拉-魁北克人工智能研究所）；Technische Hochschule Nürnberg Georg Simon Ohm（纽伦堡应用技术大学）；CIFAR AI Chair（加拿大高级研究所人工智能主席项目）
DLink: Distilling Layer-wise and Dominant Knowledge from EEG Foundation Models
Xiamen University（厦门大学）；Nanyang Technological University（南洋理工大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Southeast University（东南大学）
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…
Autonomous driving (AD) datasets have progressively grown in size in the past few years to enable better deep representation learning. Active learning (AL) has re-gained attention recently to address reduction of annotation costs and dataset size. AL has remained relatively unexplored for AD datasets, especially on point cloud data from LiDARs. This paper performs a principled evaluation of AL based dataset distillation on (1/4th) of the large Semantic-KITTI dataset. Further on, the gains in model performance due to data augmentation (DA) are demonstrated across different subsets of the AL loo…
Active Learning (AL) has remained relatively unexplored for LiDAR perception tasks in autonomous driving datasets. In this study we evaluate Bayesian active learning methods applied to the task of dataset distillation or core subset selection (subset with near equivalent performance as full dataset). We also study the effect of application of data augmentation (DA) within Bayesian AL based dataset distillation. We perform these experiments on the full Semantic-KITTI dataset. We extend our study over our existing work only on 1/4th of the same dataset. Addition of DA and BALD have a negative im…
Aalto University（阿尔托大学）；University of Manchester（曼彻斯特大学）
We introduce implicit Bayesian neural networks, a simple and scalable approach for uncertainty representation in deep learning. Standard Bayesian approach to deep learning requires the impractical inference of the posterior distribution over millions of parameters. Instead, we propose to induce a distribution that captures the uncertainty over neural networks by augmenting each layer's inputs with latent variables. We present appropriate input distributions and demonstrate state-of-the-art performance in terms of calibration, robustness and uncertainty characterisation over large-scale, multi-…
Tel Aviv University（特拉维夫大学）；Sheba Medical Center（示巴医疗中心）；Bar-Ilan University（巴伊兰大学）
In this work we propose a method for anatomical data augmentation that is based on using slices of computed tomography (CT) examinations that are adjacent to labeled slices as another resource of labeled data for training the network. The extended labeled data is used to train a U-net network for a pixel-wise classification into different hepatic lesions and normal liver tissues. Our dataset contains CT examinations from 140 patients with 333 CT images annotated by an expert radiologist. We tested our approach and compared it to the conventional training process. Results indicate superiority o…
SenseTime Research（商汤科技研究院）；Beihang University（北京航空航天大学）；University of Sydney（悉尼大学）
The recent progress on automatically searching augmentation policies has boosted the performance substantially for various tasks. A key component of automatic augmentation search is the evaluation process for a particular augmentation policy, which is utilized to return reward and usually runs thousands of times. A plain evaluation process, which includes full model training and validation, would be time-consuming. To achieve efficiency, many choose to sacrifice evaluation reliability for speed. In this paper, we dive into the dynamics of augmented training of the model. This inspires us to de…
Scalable Model Merging with Progressive Layer-wise Distillation
Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）；School of Computer Science, Beijing Institute of Technology（北京理工大学计算机学院）；Shanghai Qizhi Institute（上海启智研究院）
In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance. However, even when the prior is useful for generalization, distilling it to RL agent often interferes with RL training and degenerates sample efficiency. Meanwhile, the agent is forgetful of the prior due to the non-stationary nature of RL. These observations suggest two extreme schedules of distillation: (i) over the entire training; or (ii) only at the end. Hence, we devise a stand-alone…
Data augmentation is a key element of deep learning pipelines, as it informs the network during training about transformations of the input data that keep the label unchanged. Manually finding adequate augmentation methods and parameters for a given pipeline is however rapidly cumbersome. In particular, while intuition can guide this decision for images, the design and choice of augmentation policies remains unclear for more complex types of data, such as neuroscience signals. Besides, class-dependent augmentation strategies have been surprisingly unexplored in the literature, although it is q…
Accelerating Dataset Distillation via Model Augmentation
Zhejiang University（浙江大学）；Texas A&M University（德州农工大学）；Microsoft Research（微软研究院）；New York University（纽约大学）；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）；University of Connecticut（康涅狄格大学）；University of North Carolina, Chapel Hill（北卡罗来纳大学教堂山分校）；North Carolina State University（北卡罗来纳州立大学）
In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance. However, even when the prior is useful for generalization, distilling it to RL agent often interferes with RL training and degenerates sample efficiency. Meanwhile, the agent is forgetful of the prior due to the non-stationary nature of RL. These observations suggest two extreme schedules of distillation: (i) over the entire training; or (ii) only at the end. Hence, we devise a stand-alone…
Several solutions for lightweight TTS have shown promising results. Still, they either rely on a hand-crafted design that reaches non-optimum size or use a neural architecture search but often suffer training costs. We present Nix-TTS, a lightweight TTS achieved via knowledge distillation to a high-quality yet large-sized, non-autoregressive, and end-to-end (vocoder-free) TTS teacher model. Specifically, we offer module-wise distillation, enabling flexible and independent distillation to the encoder and decoder module. The resulting Nix-TTS inherited the advantageous properties of being non-au…
University of Guelph（圭尔夫大学）；Vector Institute for AI（人工智能向量研究所）；University of Calgary（卡尔加里大学）
Recent advancements in self-supervised learning have reduced the gap between supervised and unsupervised representation learning. However, most self-supervised and deep clustering techniques rely heavily on data augmentation, rendering them ineffective for many learning tasks where insufficient domain knowledge exists for performing augmentation. We propose a new self-distillation based algorithm for domain-agnostic clustering. Our method builds upon the existing deep clustering frameworks and requires no separate student model. The proposed method outperforms existing domain agnostic (augment…
The application of Deep Learning (DL) for medical diagnosis is often hampered by two problems. First, the amount of training data may be scarce, as it is limited by the number of patients who have acquired the condition to be diagnosed. Second, the training data may be corrupted by various types of noise. Here, we study the problem of brain tumor detection from magnetic resonance spectroscopy (MRS) data, where both types of problems are prominent. To overcome these challenges, we propose a new method for training a deep neural network that distills particularly representative training examples…
China University of Petroleum Beijing (CUP)（中国石油大学（北京））
Continual learning aims to rapidly and continually learn the current task from a sequence of tasks. Compared to other kinds of methods, the methods based on experience replay have shown great advantages to overcome catastrophic forgetting. One common limitation of this method is the data imbalance between the previous and current tasks, which would further aggravate forgetting. Moreover, how to effectively address the stability-plasticity dilemma in this setting is also an urgent problem to be solved. In this paper, we overcome these challenges by proposing a novel framework called Meta-learni…
Efficient ANN-Guided Distillation: Aligning Rate-based Features of Spiking Neural Networks through Hybrid Block-wise Replacement
ZJU-UIUC Institute, Zhejiang University（浙江大学ZJU-UIUC联合学院）；College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）
Segmentation of findings in the gastrointestinal tract is a challenging but also an important task which is an important building stone for sufficient automatic decision support systems. In this work, we present our solution for the Medico 2020 task, which focused on the problem of colon polyp segmentation. We present our simple but efficient idea of using an augmentation method that uses grids in a pyramid-like manner (large to small) for segmentation. Our results show that the proposed methods work as indented and can also lead to comparable results when competing with other methods.
Physics-Informed Neural Network Digital Twin for Dynamic Tray-Wise Modeling of Distillation Columns under Transient Operating Conditions
Department of Chemical Engineering, Veer Surendra Sai University of Technology（维杰·苏雷纳·赛大学化学工程系）；Department of Computer Science & Engineering, Veer Surendra Sai University of Technology（维杰·苏雷纳·赛大学计算机科学与工程系）
Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, China（中国科学院声学研究所语言声学与内容理解重点实验室）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学）
Incremental language learning with pseudo-data can alleviate catastrophic forgetting in neural networks. However, to obtain better performance, former methods have higher demands for pseudo-data of the previous tasks. The performance dramatically decreases when fewer pseudo-data are employed. In addition, the distribution of pseudo-data gradually deviates from the real data with the sequential learning of different tasks. The deviation will be greater with more tasks learned, which results in more serious catastrophic forgetting. To address these issues, we propose reminding incremental langua…
Yale University（耶鲁大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Automated segmentation in medical image analysis is a challenging task that requires a large amount of manually labeled data. However, most existing learning-based approaches usually suffer from limited manually annotated medical data, which poses a major practical problem for accurate and robust medical image segmentation. In addition, most existing semi-supervised approaches are usually not robust compared with the supervised counterparts, and also lack explicit modeling of geometric structure and semantic information, both of which limit the segmentation accuracy. In this work, we present S…
