Deep Learning for Weakly-Supervised Object Detection and Localization: A Survey

Feifei Shao

doi:10.1016/j.neucom.2022.01.095

Deep Learning for Weakly-Supervised Object Detection and Localization: A Survey

2022-07-01

44

PRE

AI

DOI：10.1016/j.neucom.2022.01.095

Original

Original request for help

Save

Abstract

En 中文

Weakly-Supervised Object Detection (WSOD) and Localization (WSOL), i.e., detecting multiple and single instances with bounding boxes in an image using image-level labels, are long-standing and challenging tasks in object detection. Hundreds of WSOD and WSOL methods and numerous techniques have been proposed in the deep learning era. To this end, in this paper, we consider WSOL as a sub-task of WSOD and provide a comprehensive survey of the recent achievements of WSOD. Specifically, we firstly describe the formulation and setting of the WSOD, including the background, challenges, basic framework. Meanwhile, we summarize and analyze all advanced techniques and training and test tricks for improving detection performance. Then, we introduce the widely-used datasets and evaluation metrics of WSOD. Lastly, we discuss the future directions of WSOD. We believe that these summaries can help pave a way for future research on WSOD and WSOL.(c) 2022 Elsevier B.V. All rights reserved.

Keywords:

Weakly-supervised learning

Object detection and localization

Basic framework

Techniques

Future directions

Deep Learning for Weakly-Supervised Object Detection and Localization: A Survey

Abstract

Journal

Organization