Smooth Deep Saliency
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909281289240576 |
|---|---|
| author | Herdt, Rudolf Schmidt, Maximilian Baguer, Daniel Otero Maaß, Peter |
| author_facet | Herdt, Rudolf Schmidt, Maximilian Baguer, Daniel Otero Maaß, Peter |
| contents | In this work, we investigate methods to reduce the noise in deep saliency maps coming from convolutional downsampling. Those methods make the investigated models more interpretable for gradient-based saliency maps, computed in hidden layers. We evaluate the faithfulness of those methods using insertion and deletion metrics, finding that saliency maps computed in hidden layers perform better compared to both the input layer and GradCAM. We test our approach on different models trained for image classification on ImageNet1K, and models trained for tumor detection on Camelyon16 and in-house real-world digital pathology scans of stained tissue samples. Our results show that the checkerboard noise in the gradient gets reduced, resulting in smoother and therefore easier to interpret saliency maps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_02282 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Smooth Deep Saliency Herdt, Rudolf Schmidt, Maximilian Baguer, Daniel Otero Maaß, Peter Computer Vision and Pattern Recognition In this work, we investigate methods to reduce the noise in deep saliency maps coming from convolutional downsampling. Those methods make the investigated models more interpretable for gradient-based saliency maps, computed in hidden layers. We evaluate the faithfulness of those methods using insertion and deletion metrics, finding that saliency maps computed in hidden layers perform better compared to both the input layer and GradCAM. We test our approach on different models trained for image classification on ImageNet1K, and models trained for tumor detection on Camelyon16 and in-house real-world digital pathology scans of stained tissue samples. Our results show that the checkerboard noise in the gradient gets reduced, resulting in smoother and therefore easier to interpret saliency maps. |
| title | Smooth Deep Saliency |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.02282 |