Opti-CAM: Optimizing saliency maps for interpretability
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909161341583360 |
|---|---|
| author | Zhang, Hanwei Torres, Felipe Sicre, Ronan Avrithis, Yannis Ayache, Stephane |
| author_facet | Zhang, Hanwei Torres, Felipe Sicre, Ronan Avrithis, Yannis Ayache, Stephane |
| contents | Methods based on class activation maps (CAM) provide a simple mechanism to interpret predictions of convolutional neural networks by using linear combinations of feature maps as saliency maps. By contrast, masking-based methods optimize a saliency map directly in the image space or learn it by training another network on additional data.
In this work we introduce Opti-CAM, combining ideas from CAM-based and masking-based approaches. Our saliency map is a linear combination of feature maps, where weights are optimized per image such that the logit of the masked image for a given class is maximized. We also fix a fundamental flaw in two of the most common evaluation metrics of attribution methods. On several datasets, Opti-CAM largely outperforms other CAM-based approaches according to the most relevant classification metrics. We provide empirical evidence supporting that localization and classifier interpretability are not necessarily aligned. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2301_07002 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Opti-CAM: Optimizing saliency maps for interpretability Zhang, Hanwei Torres, Felipe Sicre, Ronan Avrithis, Yannis Ayache, Stephane Computer Vision and Pattern Recognition Methods based on class activation maps (CAM) provide a simple mechanism to interpret predictions of convolutional neural networks by using linear combinations of feature maps as saliency maps. By contrast, masking-based methods optimize a saliency map directly in the image space or learn it by training another network on additional data. In this work we introduce Opti-CAM, combining ideas from CAM-based and masking-based approaches. Our saliency map is a linear combination of feature maps, where weights are optimized per image such that the logit of the masked image for a given class is maximized. We also fix a fundamental flaw in two of the most common evaluation metrics of attribution methods. On several datasets, Opti-CAM largely outperforms other CAM-based approaches according to the most relevant classification metrics. We provide empirical evidence supporting that localization and classifier interpretability are not necessarily aligned. |
| title | Opti-CAM: Optimizing saliency maps for interpretability |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2301.07002 |