Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11637-11646
Abstract
Weakly supervised object localization (WSOL) remains an open problem given the deficiency of finding object extent information using a classification network. Although prior works struggled to localize objects through various spatial regularization strategies, we argue that how to extract object structural information from the trained classification network is neglected. In this paper, we propose a two-stage approach, termed structure-preserving activation (SPA), toward fully leveraging the structure information incorporated in convolutional features for WSOL. First, a restricted activation module (RAM) is designed to alleviate the structure-missing issue caused by the classification network on the basis of the observation that the unbounded classification map and global average pooling layer drive the network to focus only on object parts. Second, we designed a post-process approach, termed self-correlation map generating (SCG) module to obtain structure-preserving localization maps on the basis of the activation maps acquired from the first stage. Specifically, we utilize the high-order self-correlation (HSC) to extract the inherent structural information retained in the learned model and then aggregate HSC of multiple points for precise object localization. Extensive experiments on two publicly available benchmarks including CUB-2002011 and ILSVRC show that the proposed SPA achieves substantial and consistent performance gains compared with baseline approaches. Code and models are available at github.com/Panxjia/SPA CVPR2021.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China
This publication has 33 references indexed in Scilit:
- Self-produced Guidance for Weakly-Supervised Object Localization2018
- Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-Supervised Object and Action Localization2017
- Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach2017
- Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation2017
- Self-Transfer Learning for Weakly Supervised Lesion Localization2016
- Rethinking the Inception Architecture for Computer Vision2016
- Learning Deep Features for Discriminative Localization2016
- Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation2015
- Constrained Convolutional Neural Networks for Weakly Supervised Segmentation2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015