Generative Adversarial Networks for Unsupervised Object Co-localization
This addresses the problem of localizing objects without labels for computer vision applications, but it is incremental as it builds on existing GAN frameworks.
The paper tackles unsupervised object co-localization by analyzing GAN discriminators, finding that high image diversity negatively correlates with localization performance, and achieves accuracy comparable to state-of-the-art weakly-supervised methods on benchmark datasets.
This paper introduces a novel approach for unsupervised object co-localization using Generative Adversarial Networks (GANs). GAN is a powerful tool that can implicitly learn unknown data distributions in an unsupervised manner. From the observation that GAN discriminator is highly influenced by pixels where objects appear, we analyze the internal layers of discriminator and visualize the activated pixels. Our important finding is that high image diversity of GAN, which is a main goal in GAN research, is ironically disadvantageous for object localization, because such discriminators focus not only on the target object, but also on the various objects, such as background objects. Based on extensive evaluations and experimental studies, we show the image diversity and localization performance have a negative correlation. In addition, our approach achieves meaningful accuracy for unsupervised object co-localization using publicly available benchmark datasets, even comparable to state-of-the-art weakly-supervised approach.