Entropy guided adversarial model for weakly supervised object localization

摘要

Weakly Supervised Object Localization is challenging due to the lack of bounding box annotations. Previous works tend to generate a Class Activation Map (CAM) to localize the object. However, the CAM highlights only the most discirminative part of the object and does not highlight the whole object. To address this problem, we propose an Entropy Guided Adversarial model (EGA model) to perform better localization of objects. EGA model uses adversarial learning method to create adversarial examples, i.e., images where a perturbation is added. Treating adversarial examples as data augmentation regularize our model as well as detect more discriminative visual pattern on the CAM. We further apply the Shannon entropy on the generated CAM to guide the model during training. Minimizing the entropy loss forces the model to generate a high-confident CAM. The high-confident CAM detects the whole object while excludes the background. Extensive experiments show that EGA model improves classification and localization performances on state-of-the-art benchmarks. Ablation experiments also show that both the adversarial learning and the entropy loss contribute to the algorithm performance. (C) 2020 Elsevier B.V. All rights reserved.