Entropy Guided Adversarial Model for Weakly Supervised Object Localization

TL;DR

This paper introduces an entropy-guided adversarial training approach for weakly supervised object localization, enhancing the network's ability to detect entire objects without altering architecture or erasing image parts.

Contribution

The paper proposes a novel entropy-guided adversarial training method that improves object localization by leveraging adversarial examples and entropy measures, without modifying network structure.

Findings

Improved localization accuracy on benchmark datasets.

Enhanced classification performance with the proposed method.

No need for architectural changes or image erasing techniques.

Abstract

Weakly Supervised Object Localization is challenging because of the lack of bounding box annotations. Previous works tend to generate a class activation map i.e CAM to localize the object. Unfortunately, the network activates only the features that discriminate the object and does not activate the whole object. Some methods tend to remove some parts of the object to force the CNN to detect other features, whereas, others change the network structure to generate multiple CAMs from different levels of the model. In this present article, we propose to take advantage of the generalization ability of the network and train the model using clean examples and adversarial examples to localize the whole object. Adversarial examples are typically used to train robust models and are images where a perturbation is added. To get a good classification accuracy, the CNN trained with adversarial examples is forced to detect more features that discriminate the object. We futher propose to apply the shannon entropy on the CAMs generated by the network to guide it during training. Our method does not erase any part of the image neither does it change the network architecure and extensive experiments show that our Entropy Guided Adversarial model (EGA model) improved performance on state of the arts benchmarks for both localization and classification accuracy.