Requirement of large annotated datasets restrict the use of deep convolutional neural networks (CNNs) for many practical applications. The problem can be mitigated by using active learning (AL) techniques which, under a given annotation budget, allow to select a subset of data that yields maximum accuracy upon fine tuning. State of the art AL approaches typically rely on measures of visual diversity or prediction uncertainty, which are unable to effectively capture the variations in spatial context. On the other hand, modern CNN architectures make heavy use of spatial context for achieving highly accurate predictions. Since the context is difficult to evaluate in the absence of ground-truth labels, we introduce the notion of contextual diversity that captures the confusion associated with spatially co-occurring classes. Contextual Diversity (CD) hinges on a crucial observation that the probability vector predicted by a CNN for a region of interest typically contains information from a larger receptive field. Exploiting this observation, we use the proposed CD measure within two AL frameworks: (1) a core-set based strategy and (2) a reinforcement learning based policy, for active frame selection. Our extensive empirical evaluation establish state of the art results for active learning on benchmark datasets of Semantic Segmentation, Object Detection and Image Classification. Our ablation studies show clear advantages of using contextual diversity for active learning. The source code and additional results are available at https://github.com/sharat29ag/CDAL.
MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval
Visual Intelligence Research Laboratories, NEC Corporation（NEC公司视觉智能研究实验室）；Graduate School of Information Sciences, Tohoku University（东北大学信息科学研究生院）；RIKEN Center for AIP（理化学研究所AIP研究中心）
Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Driving
I2R, A-STAR（新加坡科技研究局资讯通信研究院）；South China University of Technology（华南理工大学）；Southwest Jiaotong University（西南交通大学）；Chengdu University of Information Technology（成都信息工程大学）
Balancing Uncertainty and Diversity of Samples: Leveraging Diversity of Least, High Confidence Samples for Effective Active Learning
School of Computer Science and Engineering, RV University（计算机科学与工程学院，RV大学）；School of Engineering & Technology, Vidyashilp University（工程与技术学院，Vidyashilp大学）；Shiv Nadar Institution of Eminence（Shiv Nadar卓越研究院）
本文提出了一种新的混合采样方法，通过同时选择容易和困难的样本，结合多样性，以提高主动学习的效果。实验表明，所提出的Least Confident and Diverse (LCD)方法在性能上优于现有方法，通过选择不确定且多样的实例，帮助模型学习更明显的特征。
Person Re-Identification via Active Hard Sample Mining
Wuhan University of Science and Technology（武汉科技大学）；China University of Petroleum (East China)（中国石油大学（华东））；Hefei University of Technology（合肥工业大学）；Wuhan University（武汉大学）
Entropy-Guided Agreement-Diversity: A Semi-Supervised Active Learning Framework for Fetal Head Segmentation in Ultrasound
Taighde \' E ireann – Research Ireland Centre for Research Training in Machine Learning, Ireland School of Computer Science, University College Dublin, Ireland School of Medicine, University College Dublin, Ireland
