Knowledge distillation is a technique to enhance the generalization ability of a student model by exploiting outputs from a teacher model. Recently, feature-map based variants explore knowledge transfer between manually assigned teacher-student pairs in intermediate layers for further improvement. However, layer semantics may vary in different neural networks and semantic mismatch in manual layer associations will lead to performance degeneration due to negative regularization. To address this issue, we propose Semantic Calibration for cross-layer Knowledge Distillation (SemCKD), which automatically assigns proper target layers of the teacher model for each student layer with an attention mechanism. With a learned attention distribution, each student layer distills knowledge contained in multiple teacher layers rather than a specific intermediate layer for appropriate cross-layer supervision. We further provide theoretical analysis of the association weights and conduct extensive experiments to demonstrate the effectiveness of our approach. Code is avaliable at \url{https://github.com/DefangChen/SemCKD}.
Rethinking Data Distillation: Do Not Overlook Calibration
Texas A&M University（德州农工大学）；Zhejiang University（浙江大学）；Certik；University of Maryland, College Park（马里兰大学帕克分校）；Purdue University（普渡大学）；North Carolina State University（北卡罗来纳州立大学）
School of Computer Science, The University of Sydney（悉尼大学计算机科学学院）
Recent years have witnessed dramatically improvements in the knowledge distillation, which can generate a compact student model for better efficiency while retaining the model effectiveness of the teacher model. Previous studies find that: more accurate teachers do not necessary make for better teachers due to the mismatch of abilities. In this paper, we aim to analysis the phenomenon from the perspective of model calibration. We found that the larger teacher model may be too over-confident, thus the student model cannot effectively imitate. While, after the simple model calibration of the tea…
Self-Attentive Spatio-Temporal Calibration for Precise Intermediate Layer Matching in ANN-to-SNN Distillation
The College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Nanhu Brain-computer Interface Institute（南湖脑机接口研究所）；The State Key Laboratory of Brain-Machine Intelligence, Zhejiang University（浙江大学脑机智能国家重点实验室）
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…
Although recent deep learning-based calibration methods can predict extrinsic and intrinsic camera parameters from a single image, their generalization remains limited by the number and distribution of training data samples. The huge computational and space requirement prevents convolutional neural networks (CNNs) from being implemented in resource-constrained environments. This challenge motivated us to learn a CNN gradually, by training new data while maintaining performance on previously learned data. Our approach builds upon a CNN architecture to automatically estimate camera parameters (f…
Alibaba Group（阿里巴巴集团）；University of Adelaide（阿德莱德大学）
In this work, we explore data augmentations for knowledge distillation on semantic segmentation. To avoid over-fitting to the noise in the teacher network, a large number of training examples is essential for knowledge distillation. Imagelevel argumentation techniques like flipping, translation or rotation are widely used in previous knowledge distillation framework. Inspired by the recent progress on semantic directions on feature-space, we propose to include augmentations in feature space for efficient distillation. Specifically, given a semantic direction, an infinite number of augmentation…
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…
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…
LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit Calibration
Apurba-NSU R&D Lab, North South University, Bangladesh（阿普尔巴-NSU研发实验室，北南大学，孟加拉国）；Pluralis Research（普拉尔西斯研究）；Data61-CSIRO, Australia & Australian National University, Australia（Data61-CSIRO，澳大利亚及澳大利亚国立大学，澳大利亚）；Apurba Technologies, Sunnyvale, CA 94085, USA（阿普尔巴技术，硅谷，加州94085，美国）
Mutually Causal Semantic Distillation Network for Zero-Shot Learning
Huazhong University of Science and Technology（华中科技大学）；National Anti-Counterfeit Engineering Research Center（国家防伪工程技术研究中心）；Nanjing University of Science and Technology（南京理工大学）
Dynamic-Aware Video Distillation: Optimizing Temporal Resolution Based on Video Semantics
CFAR, Agency for Science, Technology and Research (A*STAR), Singapore（科技研究局（A*STAR）新加坡分部）；IHPC, Agency for Science, Technology and Research (A*STAR), Singapore（科技研究局（A*STAR）新加坡信息与通信技术中心）；School of EEE, Nanyang Technological University, Singapore（南洋理工大学电子工程学院）；CCDS, Nanyang Technological University, Singapore（南洋理工大学计算机科学与工程系）
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…
Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing
School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；School of Data Science, University of Science and Technology of China（中国科学技术大学数据科学学院）；iFLYTEK AI Research（讯飞AI研究院）
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）；Horizon Robotics（地平线机器人）；Wuhan University（武汉大学）
Current Knowledge Distillation (KD) methods for semantic segmentation often guide the student to mimic the teacher's structured information generated from individual data samples. However, they ignore the global semantic relations among pixels across various images that are valuable for KD. This paper proposes a novel Cross-Image Relational KD (CIRKD), which focuses on transferring structured pixel-to-pixel and pixel-to-region relations among the whole images. The motivation is that a good teacher network could construct a well-structured feature space in terms of global pixel dependencies. CI…
Australian National University（澳大利亚国立大学）；Data61-CSIRO Australia（澳大利亚联邦科学与工业研究组织Data61）；North South University Bangladesh（孟加拉国南北大学）；Monash University Australia（澳大利亚莫纳什大学）
Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner. Due to the limited number of examples for training, the techniques developed for standard incremental learning cannot be applied verbatim to FSCIL. In this work, we introduce a distillation algorithm to address the problem of FSCIL and propose to make use of semantic information during training. To this end, we make use of word embeddings as semantic information which is cheap to obtain and which facilitate the distillation pro…
Huazhong University of Science and Technology (HUST)（华中科技大学）；Nanjing University of Science and Technology（南京理工大学）；Nanyang Technological University（南洋理工大学）；National University of Singapore（新加坡国立大学）；Institute of North Electronic Equipment（北方电子设备研究所）
The key challenge of zero-shot learning (ZSL) is how to infer the latent semantic knowledge between visual and attribute features on seen classes, and thus achieving a desirable knowledge transfer to unseen classes. Prior works either simply align the global features of an image with its associated class semantic vector or utilize unidirectional attention to learn the limited latent semantic representations, which could not effectively discover the intrinsic semantic knowledge e.g., attribute semantics) between visual and attribute features. To solve the above dilemma, we propose a Mutually Se…
Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；ShanghaiTech University（上海科技大学）；Nanyang Technological University（南洋理工大学）
This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation. Directly employing previous distillation approaches yields inferior results due to the intrinsic challenges of point cloud, i.e., sparsity, randomness and varying density. To tackle the aforementioned problems, we propose the Point-to-Voxel Knowledge Distillation (PVD), which transfers the hidden knowledge from both point level and voxel level. Specifically, we first leverage both the pointwise and voxelwise output distillation to complement the spars…
EDITS: Enhancing Dataset Distillation with Implicit Textual Semantics
University of Electronic Science and Technology of China（电子科技大学）；Centre for Frontier AI Research, Agency for Science, Technology and Research（前沿人工智能研究中心，科技研究局）
Knowledge distillation aims to transfer knowledge to the student model by utilizing the predictions/features of the teacher model, and feature-based distillation has recently shown its superiority over logit-based distillation. However, due to the cumbersome computation and storage of extra feature transformation, the training overhead of feature-based methods is much higher than that of logit-based distillation. In this work, we revisit the logit-based knowledge distillation, and observe that the existing logit-based distillation methods treat the prediction logits only in the instance level,…
We propose an efficient way to output better calibrated uncertainty scores from neural networks. The Distilled Dropout Network (DDN) makes standard (non-Bayesian) neural networks more introspective by adding a new training loss which prevents them from being overconfident. Our method is more efficient than Bayesian neural networks or model ensembles which, despite providing more reliable uncertainty scores, are more cumbersome to train and slower to test. We evaluate DDN on the the task of image classification on the CIFAR-10 dataset and show that our calibration results are competitive even w…
School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Computer Science, The University of Sydney（悉尼大学计算机学院）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）
CEA, LIST（法国原子能与替代能源委员会 信息与技术系统实验室）；CERMICS, Ecole des Ponts（巴黎路桥学院 数学与科学计算中心）
A thorough comprehension of image content demands a complex grasp of the interactions that may occur in the natural world. One of the key issues is to describe the visual relationships between objects. When dealing with real world data, capturing these very diverse interactions is a difficult problem. It can be alleviated by incorporating common sense in a network. For this, we propose a framework that makes use of semantic knowledge and estimates the relevance of object pairs during both training and test phases. Extracted from precomputed models and training annotations, this information is …
Unsupervised Domain Adaptation (UDA) is a transfer learning task which aims at training on an unlabeled target domain by leveraging a labeled source domain. Beyond the traditional scope of UDA with a single source domain and a single target domain, real-world perception systems face a variety of scenarios to handle, from varying lighting conditions to many cities around the world. In this context, UDAs with several domains increase the challenges with the addition of distribution shifts within the different target domains. This work focuses on a novel framework for learning UDA, continuous UDA…
L2COcc: Lightweight Camera-Centric Semantic Scene Completion via Distillation of LiDAR Model
Institute of Cyber-Systems and Control, Zhejiang University（浙江大学网络系统与控制研究所）；School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）；Zhejiang Guoli Security Technology Co., Ltd.（浙江国利安全科技有限公司）
University of Toronto（多伦多大学）；Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）
An effective framework for learning 3D representations for perception tasks is distilling rich self-supervised image features via contrastive learning. However, image-to point representation learning for autonomous driving datasets faces two main challenges: 1) the abundance of self-similarity, which results in the contrastive losses pushing away semantically similar point and image regions and thus disturbing the local semantic structure of the learned representations, and 2) severe class imbalance as pretraining gets dominated by over-represented classes. We propose to alleviate the self-sim…
Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation
School of Artificial Intelligence, Xidian University, China（西安电子科技大学人工智能学院）；Department of Information Engineering and Computer Science, University of Trento, Italy（特伦托大学信息工程与计算机科学系）；Department of Automation, Tsinghua University, China（清华大学自动化系）；School of Computer Science and Information Engineering, Hefei University of Technology, China（合肥工业大学计算机科学与信息工程学院）
Generalizing WiFi Gesture Recognition via Large-Model-Aware Semantic Distillation and Alignment
Institute of Advanced Technology, University of Science and Technology of China（科学技术大学先进技术研究院）；School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机科学与信息工程学院）；School of Computer Science and Engineering, Southern University of Science and Technology（南方科技大学计算机科学与工程学院）
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））；Looko Inc.（洛可公司）
Knowledge distillation is a method of transferring the knowledge from a pretrained complex teacher model to a student model, so a smaller network can replace a large teacher network at the deployment stage. To reduce the necessity of training a large teacher model, the recent literatures introduced a self-knowledge distillation, which trains a student network progressively to distill its own knowledge without a pretrained teacher network. While Self-knowledge distillation is largely divided into a data augmentation based approach and an auxiliary network based approach, the data augmentation a…
The performance of nighttime semantic segmentation is restricted by the poor illumination and a lack of pixel-wise annotation, which severely limit its application in autonomous driving. Existing works, e.g., using the twilight as the intermediate target domain to perform the adaptation from daytime to nighttime, may fail to cope with the inherent difference between datasets caused by the camera equipment and the urban style. Faced with these two types of domain shifts, i.e., the illumination and the inherent difference of the datasets, we propose a novel domain adaptation framework via cross-…
