Cross Domain Object Detection via Multi-Granularity Confidence Alignment based Mean Teacher
National University of Defense Technology (NUDT)（国防科技大学）；College of System Engineering, National University of Defense Technology (NUDT)（国防科技大学系统工程学院）；College of Electronic Science and Technology, NUDT（国防科技大学电子科学学院）；College of Meteorology and Oceanography, NUDT（国防科技大学气象海洋学院）
Jiangming Chen, Li Liu, Wanxia Deng, Zhen Liu, Yu Liu, Yingmei Wei, Yongxiang Liu
Cross domain object detection learns an object detector for an unlabeled target domain by transferring knowledge from an annotated source domain. Promising results have been achieved via Mean Teacher, however, pseudo labeling which is the bottleneck of mutual learning remains to be further explored. In this study, we find that confidence misalignment of the predictions, including category-level overconfidence, instance-level task confidence inconsistency, and image-level confidence misfocusing, leading to the injection of noisy pseudo label in the training process, will bring suboptimal performance on the target domain. To tackle this issue, we present a novel general framework termed Multi-Granularity Confidence Alignment Mean Teacher (MGCAMT) for cross domain object detection, which alleviates confidence misalignment across category-, instance-, and image-levels simultaneously to obtain high quality pseudo supervision for better teacher-student learning. Specifically, to align confidence with accuracy at category level, we propose Classification Confidence Alignment (CCA) to model category uncertainty based on Evidential Deep Learning (EDL) and filter out the category incorrect labels via an uncertainty-aware selection strategy. Furthermore, to mitigate the instance-level misalignment between classification and localization, we design Task Confidence Alignment (TCA) to enhance the interaction between the two task branches and allow each classification feature to adaptively locate the optimal feature for the regression. Finally, we develop imagery Focusing Confidence Alignment (FCA) adopting another way of pseudo label learning, i.e., we use the original outputs from the Mean Teacher network for supervised learning without label assignment to concentrate on holistic information in the target image. These three procedures benefit from each other from a cooperative learning perspective.
University of Chinese Academy of Sciences（中国科学院大学）；ByteDance Inc（字节跳动公司）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Albeit with varying degrees of progress in the field of Semi-Supervised Semantic Segmentation, most of its recent successes are involved in unwieldy models and the lightweight solution is still not yet explored. We find that existing knowledge distillation techniques pay more attention to pixel-level concepts from labeled data, which fails to take more informative cues within unlabeled data into account. Consequently, we offer the first attempt to provide lightweight SSSS models via a novel multi-granularity distillation (MGD) scheme, where multi-granularity is captured from three aspects: i) …
Socialized UAV Cross-Task Learning: Towards Cross-Granularity Collaboration through Hierarchical Interaction
Kunming University of Science and Technology（昆明理工大学）；Tianjin University（天津大学）；University of New South Wales（新南威尔士大学）；Tianjin University of Sport（天津体育学院）；Southeast University（东南大学）；Hebei University of Technology（河北工业大学）
Pseudo-label based self training approaches are a popular method for source-free unsupervised domain adaptation. However, their efficacy depends on the quality of the labels generated by the source trained model. These labels may be incorrect with high confidence, rendering thresholding methods ineffective. In order to avoid reinforcing errors caused by label noise, we propose an uncertainty-aware mean teacher framework which implicitly filters incorrect pseudo-labels during training. Leveraging model uncertainty allows the mean teacher network to perform implicit filtering by down-weighing lo…
Fully supervised object detection requires training images in which all instances are annotated. This is actually impractical due to the high labor and time costs and the unavoidable missing annotations. As a result, the incomplete annotation in each image could provide misleading supervision and harm the training. Recent works on sparsely annotated object detection alleviate this problem by generating pseudo labels for the missing annotations. Such a mechanism is sensitive to the threshold of the pseudo label score. However, the effective threshold is different in different training stages an…
Scribble-Supervised Medical Image Segmentation with Dynamic Teacher Switching and Hierarchical Consistency
1 Carnegie Mellon University, PA 15213, United States 2 PASSIO Lab, North Carolina A\&T State University, NC 27401, United States 3 University of Houston, TX 77004, United States 4 Northwestern University, IL 60611, United States
Australian Institute for Machine Learning（澳大利亚机器学习研究所）；University of Adelaide（阿德莱德大学）；Universität Ulm（乌尔姆大学）
Consistency learning using input image, feature, or network perturbations has shown remarkable results in semi-supervised semantic segmentation, but this approach can be seriously affected by inaccurate predictions of unlabelled training images. There are two consequences of these inaccurate predictions: 1) the training based on the "strict" cross-entropy (CE) loss can easily overfit prediction mistakes, leading to confirmation bias; and 2) the perturbations applied to these inaccurate predictions will use potentially erroneous predictions as training signals, degrading consistency learning. I…
National University of Singapore（新加坡国立大学）；Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）
Object detection at night is a challenging problem due to the absence of night image annotations. Despite several domain adaptation methods, achieving high-precision results remains an issue. False-positive error propagation is still observed in methods using the well-established student-teacher framework, particularly for small-scale and low-light objects. This paper proposes a two-phase consistency unsupervised domain adaptation network, 2PCNet, to address these issues. The network employs high-confidence bounding-box predictions from the teacher in the first phase and appends them to the st…
Considering the fact that students have different abilities to understand the knowledge imparted by teachers, a multi-granularity distillation mechanism is proposed for transferring more understandable knowledge for student networks. A multi-granularity self-analyzing module of the teacher network is designed, which enables the student network to learn knowledge from different teaching patterns. Furthermore, a stable excitation scheme is proposed for robust supervision for the student training. The proposed distillation mechanism can be embedded into different distillation frameworks, which ar…
Ningbo Research Institute, Zhejiang University（浙江大学宁波研究院）；Rongcheer Co., Ltd（融澈有限公司）；Youtu Lab, Tencent（腾讯优图实验室）；Shanghai Jiao Tong University（上海交通大学）
Scale variation across object instances remains a key challenge in object detection task. Despite the remarkable progress made by modern detection models, this challenge is particularly evident in the semi-supervised case. While existing semi-supervised object detection methods rely on strict conditions to filter high-quality pseudo labels from network predictions, we observe that objects with extreme scale tend to have low confidence, resulting in a lack of positive supervision for these objects. In this paper, we propose a novel framework that addresses the scale variation problem by introdu…
AI Clearing, Inc.（AI Clearing公司）；University of Innsbruck（因斯布鲁克大学）；University of Warsaw（华沙大学）；Wageningen University & Research（瓦赫宁根大学及研究中心）
We present Polite Teacher, a simple yet effective method for the task of semi-supervised instance segmentation. The proposed architecture relies on the Teacher-Student mutual learning framework. To filter out noisy pseudo-labels, we use confidence thresholding for bounding boxes and mask scoring for masks. The approach has been tested with CenterMask, a single-stage anchor-free detector. Tested on the COCO 2017 val dataset, our architecture significantly (approx. +8 pp. in mask AP) outperforms the baseline at different supervision regimes. To the best of our knowledge, this is one of the first…
Nowadays, Semi-Supervised Object Detection (SSOD) is a hot topic, since, while it is rather easy to collect images for creating a new dataset, labeling them is still an expensive and time-consuming task. One of the successful methods to take advantage of raw images on a Semi-Supervised Learning (SSL) setting is the Mean Teacher technique, where the operations of pseudo-labeling by the Teacher and the Knowledge Transfer from the Student to the Teacher take place simultaneously. However, the pseudo-labeling by thresholding is not the best solution since the confidence value is not strictly relat…
Efficient Multi-Granularity Knowledge Transfer for Radiology Report Generation
Global College, Shanghai Jiao Tong University（上海交通大学全球学院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Ruijin Hospital, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属瑞金医院）
Teaching in adverse scenes: a statistically feedback-driven threshold and mask adjustment teacher-student framework for object detection in UAV images under adverse scenes
Southwest Jiaotong University（西南交通大学）；Chinese Academy of Surveying and Mapping（中国测绘科学研究院）
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…
Zhejiang University（浙江大学）；Hikvision Research Institute（海康威视研究院）；National University of Singapore（新加坡国立大学）；Chongqing University（重庆大学）；Hainan Institute of Zhejiang University（浙江大学海南研究院）
Self-training for unsupervised domain adaptive object detection is a challenging task, of which the performance depends heavily on the quality of pseudo boxes. Despite the promising results, prior works have largely overlooked the uncertainty of pseudo boxes during self-training. In this paper, we present a simple yet effective framework, termed as Probabilistic Teacher (PT), which aims to capture the uncertainty of unlabeled target data from a gradually evolving teacher and guides the learning of a student in a mutually beneficial manner. Specifically, we propose to leverage the uncertainty-g…
Beijing University of Posts and Telecommunications（北京邮电大学）；ByteDance（字节跳动）；USTC（中国科学技术大学）；Beijing Key Laboratory of Network System and Network Culture（北京网络系统与网络文化重点实验室）；Key Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism（文化和旅游部互动技术与体验系统重点实验室）；Zhongguancun Academy（中关村科学城）
Incremental learning methods can learn new classes continually by distilling knowledge from the last model (as a teacher model) to the current model (as a student model) in the sequentially learning process. However, these methods cannot work for Incremental Implicitly-Refined Classification (IIRC), an incremental learning extension where the incoming classes could have two granularity levels, a superclass label and a subclass label. This is because the previously learned superclass knowledge may be occupied by the subclass knowledge learned sequentially. To solve this problem, we propose a no…
Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution
Hong Kong University of Science and Technology (GZ)（香港科技大学（广州））；Southern University of Science and Technology（南方科技大学）；East China Normal University（华东师范大学）
Addressing data annotation scarcity in Brain Tumor Segmentation on 3D MRI scan Using a Semi-Supervised Teacher-Student Framework
College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics（人工智能学院，南京航空航天大学）；Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education（脑机智能技术重点实验室，教育部）；Shenzhen Research Institute, Nanjing University of Aeronautics and Astronautics（深圳研究院，南京航空航天大学）
CoDiR: Confidence-Guided Diffusion Refinement for Semi-Supervised Histopathology Segmentation
AI VIETNAM Lab（AI VIETNAM实验室）；Portland Community College（波特兰社区学院）；University of Science, VNU-HCM（胡志明市国家大学科学大学）；Hanoi University of Science and Technology（河内科技大学）；Jeonbuk National University（全北国立大学）；Washington University School of Medicine（华盛顿大学医学院）；Perelman School of Medicine, University of Pennsylvania（宾夕法尼亚大学佩雷尔曼医学院）
Knowledge distillation aims at obtaining a compact and effective model by learning the mapping function from a much larger one. Due to the limited capacity of the student, the student would underfit the teacher. Therefore, student performance would unexpectedly drop when distilling from an oversized teacher, termed the capacity gap problem. We investigate this problem by study the gap of confidence between teacher and student. We find that the magnitude of confidence is not necessary for knowledge distillation and could harm the student performance if the student are forced to learn confidence…
This technical report presents an overview of our solution used in the submission to ActivityNet Challenge 2019 Task 1 (\textbf{temporal action proposal generation}) and Task 2 (\textbf{temporal action localization/detection}). Temporal action proposal indicates the temporal intervals containing the actions and plays an important role in temporal action localization. Top-down and bottom-up methods are the two main categories used for proposal generation in the existing literature. In this paper, we devise a novel Multi-Granularity Fusion Network (MGFN) to combine the proposals generated from d…
Data-efficient domain adaptation with only a few labelled data is desired for many robotic applications, e.g., in grasping detection, the inference skill learned from a grasping dataset is not universal enough to directly apply on various other daily/industrial applications. This paper presents an approach enabling the easy domain adaptation through a novel grasping detection network with confidence-driven semi-supervised learning, where these two components deeply interact with each other. The proposed grasping detection network specially provides a prediction uncertainty estimation mechanism…
In this paper, a novel confidence conditioned knowledge distillation (CCKD) scheme for transferring the knowledge from a teacher model to a student model is proposed. Existing state-of-the-art methods employ fixed loss functions for this purpose and ignore the different levels of information that need to be transferred for different samples. In addition to that, these methods are also inefficient in terms of data usage. CCKD addresses these issues by leveraging the confidence assigned by the teacher model to the correct class to devise sample-specific loss functions (CCKD-L formulation) and ta…
VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree
School of Software, Xi’an Jiaotong University（西安交通大学软件学院）；China Railway Xi’an Group（中国铁路西安集团）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）
MMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language Models
The City University of New York, CUNY（纽约城市大学）；Nanyang Technological University（南洋理工大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Technology Sydney（悉尼技术大学）；Data61, CSIRO（CSIRO数据61研究所）；Shenzhen University of Advanced Technology（深圳先进技术大学）
TiS-TSL: Image-Label Supervised Surgical Video Stereo Matching via Time-Switchable Teacher-Student Learning
Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology（华中科技大学光电实验室）；Wuhan United Imaging Surgical Co., Ltd.（武汉联合影像手术有限公司）
Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs
Department of Information Technology（信息科技系）；Electrical Engineering, ETH Zurich, Zurich, Switzerland（电气工程，苏黎世联邦理工学院，苏黎世，瑞士）；Qualcomm AI Research, Amsterdam, the Netherlands（高通人工智能研究，阿姆斯特丹，荷兰）；Department of Electrical, Electronic and Information Engineering（电气、电子与信息工程系）；University of Bologna, Bologna, Italy（博洛尼亚大学，博洛尼亚，意大利）；School of Electrical and Electronic Engineering（电气与电子工程学院）
The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Stanford University（斯坦福大学）
Annotation scarcity is a long-standing problem in medical image analysis area. To efficiently leverage limited annotations, abundant unlabeled data are additionally exploited in semi-supervised learning, while well-established cross-modality data are investigated in domain adaptation. In this paper, we aim to explore the feasibility of concurrently leveraging both unlabeled data and cross-modality data for annotation-efficient cardiac segmentation. To this end, we propose a cutting-edge semi-supervised domain adaptation framework, namely Dual-Teacher++. Besides directly learning from limited l…
Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation of Chinese Academy of Sciences（中国科学院自动化研究所）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
