ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917618887163904 |
|---|---|
| author | Chakraborty, Rwiddhi Sletten, Adrian Kampffmeyer, Michael |
| author_facet | Chakraborty, Rwiddhi Sletten, Adrian Kampffmeyer, Michael |
| contents | Group robustness strategies aim to mitigate learned biases in deep learning models that arise from spurious correlations present in their training datasets. However, most existing methods rely on the access to the label distribution of the groups, which is time-consuming and expensive to obtain. As a result, unsupervised group robustness strategies are sought. Based on the insight that a trained model's classification strategies can be inferred accurately based on explainability heatmaps, we introduce ExMap, an unsupervised two stage mechanism designed to enhance group robustness in traditional classifiers. ExMap utilizes a clustering module to infer pseudo-labels based on a model's explainability heatmaps, which are then used during training in lieu of actual labels. Our empirical studies validate the efficacy of ExMap - We demonstrate that it bridges the performance gap with its supervised counterparts and outperforms existing partially supervised and unsupervised methods. Additionally, ExMap can be seamlessly integrated with existing group robustness learning strategies. Finally, we demonstrate its potential in tackling the emerging issue of multiple shortcut mitigation\footnote{Code available at \url{https://github.com/rwchakra/exmap}}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_13870 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations Chakraborty, Rwiddhi Sletten, Adrian Kampffmeyer, Michael Computer Vision and Pattern Recognition Machine Learning Group robustness strategies aim to mitigate learned biases in deep learning models that arise from spurious correlations present in their training datasets. However, most existing methods rely on the access to the label distribution of the groups, which is time-consuming and expensive to obtain. As a result, unsupervised group robustness strategies are sought. Based on the insight that a trained model's classification strategies can be inferred accurately based on explainability heatmaps, we introduce ExMap, an unsupervised two stage mechanism designed to enhance group robustness in traditional classifiers. ExMap utilizes a clustering module to infer pseudo-labels based on a model's explainability heatmaps, which are then used during training in lieu of actual labels. Our empirical studies validate the efficacy of ExMap - We demonstrate that it bridges the performance gap with its supervised counterparts and outperforms existing partially supervised and unsupervised methods. Additionally, ExMap can be seamlessly integrated with existing group robustness learning strategies. Finally, we demonstrate its potential in tackling the emerging issue of multiple shortcut mitigation\footnote{Code available at \url{https://github.com/rwchakra/exmap}}. |
| title | ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2403.13870 |