MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization

by   Kaili Wang, et al.

One of the most common problems of weakly supervised object localization is that of inaccurate object coverage. In the context of state-of-the-art methods based on Class Activation Mapping, this is caused either by localization maps which focus, exclusively, on the most discriminative region of the objects of interest or by activations occurring in background regions. To address these two problems, we propose two representation regularization mechanisms: Full Region Regularizationwhich tries to maximize the coverage of the localization map inside the object region, and Common Region Regularization which minimizes the activations occurring in background regions. We evaluate the two regularizations on the ImageNet, CUB-200-2011 and OpenImages-segmentation datasets, and show that the proposed regularizations tackle both problems, outperforming the state-of-the-art by a significant margin.


page 2

page 4

page 6


Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization

Weakly supervised object localization aims to find a target object regio...

ViTOL: Vision Transformer for Weakly Supervised Object Localization

Weakly supervised object localization (WSOL) aims at predicting object l...

Density-Based Region Search with Arbitrary Shape for Object Localization

Region search is widely used for object localization. Typically, the reg...

Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation

Weakly supervised image segmentation trained with image-level labels usu...

Cross Language Image Matching for Weakly Supervised Semantic Segmentation

It has been widely known that CAM (Class Activation Map) usually only ac...

Dual-attention Focused Module for Weakly Supervised Object Localization

The research on recognizing the most discriminative regions provides ref...

A Holistic Approach for Data-Driven Object Cutout

Object cutout is a fundamental operation for image editing and manipulat...