Visual Feature Attribution using Wasserstein GANs

Attributing the pixels of an input image to a certain category is an important and well-studied problem in computer vision, with applications ranging from weakly supervised localization to understanding hidden effects in the data. In recent years, approaches based on interpreting a previously trained neural network classifier have become the de facto state-of-the-art and are commonly used on medical as well as natural image datasets. In this paper, the authors discuss a limitation of these approaches which may lead to only a subset of the category specific features being detected. To address this problem they develop a novel feature attribution technique based on Wasserstein Generative Adversarial Networks (WGAN), which does not suffer from this limitation.


Want to receive more content like this in your inbox?