Background-aware Classification Activation Map for Weakly Supervised Object Localization

by   Lei Zhu, et al.

Weakly supervised object localization (WSOL) relaxes the requirement of dense annotations for object localization by using image-level classification masks to supervise its learning process. However, current WSOL methods suffer from excessive activation of background locations and need post-processing to obtain the localization mask. This paper attributes these issues to the unawareness of background cues, and propose the background-aware classification activation map (B-CAM) to simultaneously learn localization scores of both object and background with only image-level labels. In our B-CAM, two image-level features, aggregated by pixel-level features of potential background and object locations, are used to purify the object feature from the object-related background and to represent the feature of the pure-background sample, respectively. Then based on these two features, both the object classifier and the background classifier are learned to determine the binary object localization mask. Our B-CAM can be trained in end-to-end manner based on a proposed stagger classification loss, which not only improves the objects localization but also suppresses the background activation. Experiments show that our B-CAM outperforms one-stage WSOL methods on the CUB-200, OpenImages and VOC2012 datasets.


page 2

page 4

page 5

page 6

page 8

page 11

page 13


Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization

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

Background Activation Suppression for Weakly Supervised Object Localization

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

Geometry Constrained Weakly Supervised Object Localization

We propose a geometry constrained network, termed GC-Net, for weakly sup...

Equivalent Classification Mapping for Weakly Supervised Temporal Action Localization

Weakly supervised temporal action localization is a newly emerging yet w...

Normalization Matters in Weakly Supervised Object Localization

Weakly-supervised object localization (WSOL) enables finding an object u...

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

Weakly supervised object localization remains an open problem due to the...

Eigen-CAM: Class Activation Map using Principal Components

Deep neural networks are ubiquitous due to the ease of developing models...

Please sign up or login with your details

Forgot password? Click here to reset