Classifier-agnostic saliency map extraction

Abstract

Currently available methods for extracting saliency maps identify parts of the input which are the most important to a specific fixed classifier. We show that this strong dependence on a given classifier hinders their performance. To address this problem, 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 than prior work while being conceptually simple and easy to implement. The method sets the new state of the art result for localization task on the ImageNet data, outperforming all existing weakly-supervised localization techniques, despite not using the ground truth labels at the inference time. The code reproducing the results is available at https://github.com/kondiz/casme . The final version of this manuscript is published in Computer Vision and Image Understanding and is available online at https://doi.org/10.1016/j.cviu.2020.102969 .

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Striving for Simplicity: The All Convolutional Net
• Context Proposals for Saliency Detection
• Salient Region Segmentation
• "Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors

Cited by in corpus (6)

• Accurate Virus Identification with Interpretable Raman Signatures by Machine Learning
• On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition
• The Unreasonable Effectiveness of Deep Evidential Regression
• Investigating and Simplifying Masking-based Saliency Methods for Model Interpretability
• Contributions to Large Scale Bayesian Inference and Adversarial Machine Learning
• Multivariate Deep Evidential Regression