Information-Bottleneck Approach to Salient Region Discovery
Abstract
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.
Cite
Text
Zhmoginov et al. "Information-Bottleneck Approach to Salient Region Discovery." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2020. doi:10.1007/978-3-030-67664-3_32Markdown
[Zhmoginov et al. "Information-Bottleneck Approach to Salient Region Discovery." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2020.](https://mlanthology.org/ecmlpkdd/2020/zhmoginov2020ecmlpkdd-informationbottleneck/) doi:10.1007/978-3-030-67664-3_32BibTeX
@inproceedings{zhmoginov2020ecmlpkdd-informationbottleneck,
title = {{Information-Bottleneck Approach to Salient Region Discovery}},
author = {Zhmoginov, Andrey and Fischer, Ian and Sandler, Mark},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2020},
pages = {531-546},
doi = {10.1007/978-3-030-67664-3_32},
url = {https://mlanthology.org/ecmlpkdd/2020/zhmoginov2020ecmlpkdd-informationbottleneck/}
}