Information-Bottleneck Approach to Salient Region Discovery
By Andrey Zhmoginov, Ian S. Fischer, Mark Sandler. 2019
20 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Hannaneh Hajishirzi
- Luke S. Zettlemoyer
- Luc Van Gool
- Trevor Darrell
- Dacheng Tao
- Ming-Hsuan Yang
- Mohit Bansal
- Xiaogang Wang
Citations in the corpus
- On the Binding Problem in Artificial Neural Networks (2020, background): “by highlighting locations that are (maximally) informative with respect to a discriminative task (Gao and Vasconcelos, 2005; Cao et al., 2015; Zhmoginov et al., 2019).”
- An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction (2020, methodology): “Information Bottleneck The Information Bot-tleneck (IB) principle (Tishby et al., 1999) has recently been adapted in a number of downstream applications like parsing (Li and Eisner, 2019), summarization (West et al., 2019), and image classifi-cation (Alemi et al., 2016; Zhmoginov et al., 2019).”
- Unsupervised Object Keypoint Learning using Local Spatial Predictability (2020, methodology): “For example, Bruce & Tsotsos (2005) use Shannon’s self information metric as a measure of saliency, while Zhmoginov et al. (2019) leverage mutual information to guide saliency masks.”