Improve CAM with Auto-adapted Segmentation and Co-supervised Augmentation

TL;DR

This paper introduces a novel approach for Weakly Supervised Object Localization that enhances CAM by incorporating confidence segmentation and co-supervised augmentation, leading to state-of-the-art results.

Contribution

It proposes ConfSeg and CoAug modules that improve foreground-background separation and localization accuracy without extra hyper-parameters.

Findings

Achieves 37.69% Top-1 localization error on CUB-200

Achieves 48.81% Top-1 localization error on ILSVRC

Outperforms previous WSOL methods significantly

Abstract

Weakly Supervised Object Localization (WSOL) methods generate both classification and localization results by learning from only image category labels. Previous methods usually utilize class activation map (CAM) to obtain target object regions. However, most of them only focus on improving foreground object parts in CAM, but ignore the important effect of its background contents. In this paper, we propose a confidence segmentation (ConfSeg) module that builds confidence score for each pixel in CAM without introducing additional hyper-parameters. The generated sample-specific confidence mask is able to indicate the extent of determination for each pixel in CAM, and further supervises additional CAM extended from internal feature maps. Besides, we introduce Co-supervised Augmentation (CoAug) module to capture feature-level representation for foreground and background parts in CAM separately. Then a metric loss is applied at batch sample level to augment distinguish ability of our model, which helps a lot to localize more related object parts. Our final model, CSoA, combines the two modules and achieves superior performance, e.g. $37.69\%$ and $48.81\%$ Top-1 localization error on CUB-200 and ILSVRC datasets, respectively, which outperforms all previous methods and becomes the new state-of-the-art.