Classifier-agnostic saliency map extractionDownload PDF

27 Sep 2018 (modified: 18 Oct 2019)ICLR 2019 Conference Blind SubmissionReaders: Everyone
  • Abstract: Extracting saliency maps, which indicate parts of the image important to classification, requires many tricks to achieve satisfactory performance when using classifier-dependent methods. Instead, we propose classifier-agnostic saliency map extraction, which finds all parts of the image that any classifier could use, not just one given in advance. We observe that the proposed approach extracts higher quality saliency maps and outperforms existing weakly-supervised localization techniques, setting the new state of the art result on the ImageNet dataset.
  • Keywords: saliency maps, explainable AI, convolutional neural networks, generative adversarial training, classification
  • TL;DR: We propose a new saliency map extraction method which results in extracting higher quality maps.
10 Replies