Bias Identification with RankPix Saliency

Saliency methods are critical tools that allow the estimation of the most important features of an input image that contribute to the network's prediction. These tools are pivotal in high-stakes applications such as medical diagnosis or autonomous driving. Additionally, these tools can help ide...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 1 - 5
Main Authors Konate, Salamata, Lebrat, Leo, Cruz, Rodrigo Santa, Fookes, Clinton, Bradley, Andrew, Salvado, Olivier
Format Conference Proceeding
LanguageEnglish
Published IEEE 04.06.2023
Subjects
Benchmark testing
Bias identification
Explainability
Games
Reliability
Saliency method
Signal processing
Systematics
Training
Visualization
Online AccessGet full text

Cover

More Information
Summary:Saliency methods are critical tools that allow the estimation of the most important features of an input image that contribute to the network's prediction. These tools are pivotal in high-stakes applications such as medical diagnosis or autonomous driving. Additionally, these tools can help identify models' biasedness, such as a strong prior on object placement, easily distinguishable background features, or frequent object co-occurrence. We introduce RankPix, a novel saliency method for visual bias identification in image classification tasks. RankPix is a derivative-free approach that allows the identification of a minimum subset of pixels/features at a given network layer that changes the output of a classifier. Surprisingly, this approaches provides equivalent performance to gradient-based approaches on the standard pointing game benchmark. More interestingly, RankPix outperforms traditional approaches for systematic bias identification.
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10097093