Unveiling the Potential of Structure-Preserving for Weakly Supervised Object Localization

by   Xingjia Pan, et al.

Weakly supervised object localization remains an open problem due to the deficiency of finding object extent information using a classification network. While prior works struggle to localize objects by 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), towards fully leveraging the structure information incorporated in convolutional features for WSOL. In the first stage, a restricted activation module (RAM) is designed to alleviate the structure-missing issue caused by the classification network, based on the observation that the unbounded classification map and global average pooling layer drive the network to focus only on object parts. In the second stage, we propose 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-200-2011 and ILSVRC show that the proposed SPA achieves substantial and consistent performance gains compared with baseline approaches.


page 3

page 5

page 7

page 8

page 14

page 15

page 16

page 17


Background Activation Suppression for Weakly Supervised Object Localization

Weakly supervised object localization (WSOL) aims to localize the object...

Background-aware Classification Activation Map for Weakly Supervised Object Localization

Weakly supervised object localization (WSOL) relaxes the requirement of ...

Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization

Classification activation map (CAM), utilizing the classification struct...

Re-Attention Transformer for Weakly Supervised Object Localization

Weakly supervised object localization is a challenging task which aims t...

Self-produced Guidance for Weakly-supervised Object Localization

Weakly supervised methods usually generate localization results based on...

Object-Extent Pooling for Weakly Supervised Single-Shot Localization

In the face of scarcity in detailed training annotations, the ability to...

Entropy Guided Adversarial Model for Weakly Supervised Object Localization

Weakly Supervised Object Localization is challenging because of the lack...

Please sign up or login with your details

Forgot password? Click here to reset