Information-Bottleneck Approach to Salient Region Discovery

• Main Authors: Zhmoginov, Andrey, Fischer, Ian, Sandler, Mark
• Format: Journal Article
• Language: English
• Published: 22-07-2019
• Subjects: Computer Science - Computer Vision and Pattern Recognition; Computer Science - Information Theory; Computer Science - Learning; Mathematics - Information Theory
• DOI: 10.48550/arxiv.1907.09578

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.