With the success of deep neural networks, knowledge distillation which guides the learning of a small student network from a large teacher network is being actively studied for model compression and transfer learning. However, few studies have been performed to resolve the poor learning issue of the student network when the student and teacher model sizes significantly differ. In this paper, we propose a densely guided knowledge distillation using multiple teacher assistants that gradually decreases the model size to efficiently bridge the large gap between the teacher and student networks. To stimulate more efficient learning of the student network, we guide each teacher assistant to every other smaller teacher assistants iteratively. Specifically, when teaching a smaller teacher assistant at the next step, the existing larger teacher assistants from the previous step are used as well as the teacher network. Moreover, we design stochastic teaching where, for each mini-batch, a teacher or teacher assistants are randomly dropped. This acts as a regularizer to improve the efficiency of teaching of the student network. Thus, the student can always learn salient distilled knowledge from the multiple sources. We verified the effectiveness of the proposed method for a classification task using CIFAR-10, CIFAR-100, and ImageNet. We also achieved significant performance improvements with various backbone architectures such as ResNet, WideResNet, and VGG.
In this paper, we propose an approach for filter-level pruning with hierarchical knowledge distillation based on the teacher, teaching-assistant, and student framework. Our method makes use of teaching assistants at intermediate pruning levels that share the same architecture and weights as the target student. We propose to prune each model independently using the gradient information from its corresponding teacher. By considering the relative sizes of each student-teacher pair, this formulation provides a natural trade-off between the capacity gap for knowledge distillation and the bias of th…
Pohang University of Science Technology (POSTECH)（浦项科技大学）
Semi-supervised domain adaptation (SSDA) is to adapt a learner to a new domain with only a small set of labeled samples when a large labeled dataset is given on a source domain. In this paper, we propose a pair-based SSDA method that adapts a model to the target domain using self-distillation with sample pairs. Each sample pair is composed of a teacher sample from a labeled dataset (i.e., source or labeled target) and its student sample from an unlabeled dataset (i.e., unlabeled target). Our method generates an assistant feature by transferring an intermediate style between the teacher and the…
MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection
National Yang Ming Chiao Tung University（国立阳明交通大学）；University of Washington（华盛顿大学）；University of Southern California（南加州大学）；Cisco Systems, Inc.（思科系统公司）；Taijitu AI, Inc.（太极图人工智能公司）；National Taiwan Normal University（国立台湾师范大学）；National Taiwan University（国立台湾大学）
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）
Multi-lingual script identification is a difficult task consisting of different language with complex backgrounds in scene text images. According to the current research scenario, deep neural networks are employed as teacher models to train a smaller student network by utilizing the teacher model's predictions. This process is known as dark knowledge transfer. It has been quite successful in many domains where the final result obtained is unachievable through directly training the student network with a simple architecture. In this paper, we explore dark knowledge transfer approach using long …
Knowledge distillation (KD) is an effective tool for compressing deep classification models for edge devices. However, the performance of KD is affected by the large capacity gap between the teacher and student networks. Recent methods have resorted to a multiple teacher assistant (TA) setting for KD, which sequentially decreases the size of the teacher model to relatively bridge the size gap between these models. This paper proposes a new technique called Curriculum Expert Selection for Knowledge Distillation (CES-KD) to efficiently enhance the learning of a compact student under the capacity…
University of Southern California（南加州大学）；Google Research（谷歌研究院）
Fine-grained image labels are desirable for many computer vision applications, such as visual search or mobile AI assistant. These applications rely on image classification models that can produce hundreds of thousands (e.g. 100K) of diversified fine-grained image labels on input images. However, training a network at this vocabulary scale is challenging, and suffers from intolerable large model size and slow training speed, which leads to unsatisfying classification performance. A straightforward solution would be training separate expert networks (specialists), with each specialist focusing …
The Chinese University of Hong Kong（香港中文大学）；Shanghai AI Laboratory（上海人工智能实验室）
Semi-Supervised Semantic Segmentation aims at training the segmentation model with limited labeled data and a large amount of unlabeled data. To effectively leverage the unlabeled data, pseudo labeling, along with the teacher-student framework, is widely adopted in semi-supervised semantic segmentation. Though proved to be effective, this paradigm suffers from incorrect pseudo labels which inevitably exist and are taken as auxiliary training data. To alleviate the negative impact of incorrect pseudo labels, we delve into the current Semi-Supervised Semantic Segmentation frameworks. We argue th…
Insight SFI Research Centre for Data Analytics（Insight SFI数据分析研究中心）；Dublin City University（都柏林城市大学）；University of Catania（卡塔尼亚大学）
Video saliency prediction has recently attracted attention of the research community, as it is an upstream task for several practical applications. However, current solutions are particularly computationally demanding, especially due to the wide usage of spatio-temporal 3D convolutions. We observe that, while different model architectures achieve similar performance on benchmarks, visual variations between predicted saliency maps are still significant. Inspired by this intuition, we propose a lightweight model that employs multiple simple heterogeneous decoders and adopts several practical app…
Beihang University（北京航空航天大学）；SenseTime Research（商汤科技研究院）；ETH Zurich（苏黎世联邦理工学院）；Shandong University（山东大学）；University of Science and Technology of China（中国科学技术大学）
Conventional knowledge distillation (KD) methods for object detection mainly concentrate on homogeneous teacher-student detectors. However, the design of a lightweight detector for deployment is often significantly different from a high-capacity detector. Thus, we investigate KD among heterogeneous teacher-student pairs for a wide application. We observe that the core difficulty for heterogeneous KD (hetero-KD) is the significant semantic gap between the backbone features of heterogeneous detectors due to the different optimization manners. Conventional homogeneous KD (homo-KD) methods suffer …
Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learning
Nagoya University（名古屋大学）；Northeastern University（东北大学）；KC Machine Learning Lab（KC机器学习实验室）；University of Science, Vietnam National University Ho Chi Minh City（胡志明市越南国立大学理科大学）；University of California, Los Angeles（加州大学洛杉矶分校）
In this paper, we propose a new continuously learning generative model, called the Lifelong Twin Generative Adversarial Networks (LT-GANs). LT-GANs learns a sequence of tasks from several databases and its architecture consists of three components: two identical generators, namely the Teacher and Assistant, and one Discriminator. In order to allow for the LT-GANs to learn new concepts without forgetting, we introduce a new lifelong training approach, namely Lifelong Adversarial Knowledge Distillation (LAKD), which encourages the Teacher and Assistant to alternately teach each other, while lear…
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）
Tianjin University（天津大学）；The Chinese University of Hong Kong（香港中文大学）；SenseTime Group Limited（商汤科技集团有限公司）；Nanyang Technological University（南洋理工大学）
Knowledge distillation (KD) is one of the most potent ways for model compression. The key idea is to transfer the knowledge from a deep teacher model (T) to a shallower student (S). However, existing methods suffer from performance degradation due to the substantial gap between the learning capacities of S and T. To remedy this problem, this work proposes Residual Knowledge Distillation (RKD), which further distills the knowledge by introducing an assistant (A). Specifically, S is trained to mimic the feature maps of T, and A aids this process by learning the residual error between them. In th…
Sun Yat-Sen University（中山大学）；DarkMatter AI Research
Crowd counting is an application-oriented task and its inference efficiency is crucial for real-world applications. However, most previous works relied on heavy backbone networks and required prohibitive run-time consumption, which would seriously restrict their deployment scopes and cause poor scalability. To liberate these crowd counting models, we propose a novel Structured Knowledge Transfer (SKT) framework, which fully exploits the structured knowledge of a well-trained teacher network to generate a lightweight but still highly effective student network. Specifically, it is integrated wit…
Lecture slide presentations, a sequence of pages that contain text and figures accompanied by speech, are constructed and presented carefully in order to optimally transfer knowledge to students. Previous studies in multimedia and psychology attribute the effectiveness of lecture presentations to their multimodal nature. As a step toward developing AI to aid in student learning as intelligent teacher assistants, we introduce the Multimodal Lecture Presentations dataset as a large-scale benchmark testing the capabilities of machine learning models in multimodal understanding of educational cont…
Look One and More: Distilling Hybrid Order Relational Knowledge for Cross-Resolution Image Recognition
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Beijing Electronic Science and Technology Institute（北京电子科技学院）；CloudWalk Technology Co., Ltd（云从科技股份有限公司）
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, China（通用人工智能国家重点实验室，智能科学与技术学院，北京大学，中国）；Huawei Noah’s Ark Lab, China（华为诺亚方舟实验室，中国）
Understanding complex scenarios from in-vehicle cameras is essential for safely operating autonomous driving systems in densely populated areas. Among these, intersection areas are one of the most critical as they concentrate a considerable number of traffic accidents and fatalities. Detecting and understanding the scene configuration of these usually crowded areas is then of extreme importance for both autonomous vehicles and modern ADAS aimed at preventing road crashes and increasing the safety of vulnerable road users. This work investigates inter-section classification from RGB images usin…
