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

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.

arXiv commentAccepted by WACV2021. Equal contribution for the first two authors

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
• Going Deeper with Convolutions
• Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features
• Deep Self-Taught Learning for Weakly Supervised Object Localization
• Self-produced Guidance for Weakly-supervised Object Localization
• Combinational Class Activation Maps for Weakly Supervised Object Localization