When we can not assume a large amount of annotated data , active learning is a good strategy. It consists in learning a model on a small amount of annotated data (annotation budget) and in choosing the best set of points to annotate in order to improve the previous model and gain in generalization. In deep learning, active learning is usually implemented as an iterative process in which successive deep models are updated via fine tuning, but it still poses some issues. First, the initial batch of annotated images has to be sufficiently large to train a deep model. Such an assumption is strong, especially when the total annotation budget is reduced. We tackle this issue by using an approach inspired by transfer learning. A pre-trained model is used as a feature extractor and only shallow classifiers are learned during the active iterations. The second issue is the effectiveness of probability or feature estimates of early models for AL task. Samples are generally selected for annotation using acquisition functions based only on the last learned model. We introduce a novel acquisition function which exploits the iterative nature of AL process to select samples in a more robust fashion. Samples for which there is a maximum shift towards uncertainty between the last two learned models predictions are favored. A diversification step is added to select samples from different regions of the classification space and thus introduces a representativeness component in our approach. Evaluation is done against competitive methods with three balanced and imbalanced datasets and outperforms them.
Embodied Active Learning under Limited Annotation and Navigation Budget for Object Detection
LAAS-CNRS, Universite de Toulouse, CNRS（法国国家科学研究中心图卢兹分部LAAS、图卢兹大学、法国国家科学研究中心）；Department of Electrical Engineering and Automation at Aalto University（阿尔托大学电气工程与自动化系）
Urban Scene Semantic Segmentation with Low-Cost Coarse Annotation
MPI for Informatics（马克斯·普朗克信息学研究所）；Saarland Informatics Campus（萨尔兰信息学园区）；ETH Zürich（苏黎世联邦理工学院）；CISPA（亥姆霍兹信息安全中心）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Tübingen（蒂宾根大学）
How to Efficiently Annotate Images for Best-Performing Deep Learning Based Segmentation Models: An Empirical Study with Weak and Noisy Annotations and Segment Anything Model
Slide-Level Active Learning Reduces Annotation Burden in H&E images
Institute for Biomedical Informatics, Faculty of Medicine（生物医学信息学研究所，医学学院）；University Hospital Cologne, University of Cologne（科隆大学医院，科隆大学）；Center for Molecular Medicine Cologne (CMMC), Faculty of Medicine（科隆分子医学中心（CMMC），医学学院）；Cologne Excellence Cluster on Cellular Stress Responses in Aging-Associated Diseases (CECAD), University of Cologne（科隆卓越集群：与衰老相关疾病细胞应激反应（CECAD），科隆大学）；Faculty of Mathematics（数学学院）；Natural Sciences, University of Cologne（自然科学学院，科隆大学）；Institute of Pathology, University Hospital Cologne（病理学研究所，科隆大学医院）
Tsinghua University（清华大学）；BNRist（北京国家信息科学与技术研究中心）；Hangzhou Zhuoxi Institute of Brain and Intelligence（杭州卓识脑与智能研究院）；OPPO Research Institute（OPPO研究院）；Beijing University of Posts and Telecommunications（北京邮电大学）
Enhancing Semi-Supervised Learning via Representative and Diverse Sample Selection
BNU-HKBU United International College（北京师范大学-香港浸会大学联合国际学院）；WeDoctor Cloud（微医云）；The State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全国家重点实验室）
