Information-Bottleneck Approach to Salient Region Discovery

We propose a new method for learning image attention masks in a semi-supervised setting based on the Information Bottleneck principle. Provided with a set of labeled images, the mask generation model is minimizing mutual information between the input and the masked image while maximizing the mutual information between the same masked image and the image label. In contrast with other approaches, our attention model produces a Boolean rather than a continuous mask, entirely concealing the information in masked-out pixels. Using a set of synthetic datasets based on MNIST and CIFAR10 and the SVHN datasets, we demonstrate that our method can successfully attend to features known to define the image class.

Automated summary

This new method utilizes the Information Bottleneck principle to generate image attention masks in a semi-supervised setting, producing Boolean masks that conceal information in masked-out pixels effectively. It has been demonstrated to successfully attend to features defining the image class in synthetic datasets based on MNIST, CIFAR10, and SVHN datasets.