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

by   Feifei Shao, et al.

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 the CV community. With the success of deep neural networks in object detection, both WSOD and WSOL have received unprecedented attention. 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 is 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 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.


page 1

page 2

page 3


Weakly Supervised Object Detection with Segmentation Collaboration

Weakly supervised object detection aims at learning precise object detec...

Recent Advances in Deep Learning for Object Detection

Object detection is a fundamental visual recognition problem in computer...

Deep Learning for Generic Object Detection: A Survey

Generic object detection, aiming at locating object instances from a lar...

SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection

Based on the framework of multiple instance learning (MIL), tremendous w...

Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection

Weakly Supervised Object Detection (WSOD) has emerged as an effective to...

A Survey of Modern Deep Learning based Object Detection Models

Object Detection is the task of classification and localization of objec...

Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection

This paper reports a new solution of leveraging temporal classification ...