Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.24117 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912981722333184 |
|---|---|
| author | Faget, David Lisani, José Luis Colom, Miguel |
| author_facet | Faget, David Lisani, José Luis Colom, Miguel |
| contents | Planet-scale photo geolocalization involves the intricate task of estimating the geographic location depicted in an image purely based on its visual features. While deep learning models, particularly convolutional neural networks (CNNs), have significantly advanced this field, understanding the reasoning behind their predictions remains challenging. In this paper, we present Combi-CAM, a novel method that enhances the explainability of CNN-based geolocalization models by combining gradient-weighted class activation maps obtained from several layers of the network architecture, rather than using only information from the deepest layer as is typically done. This approach provides a more detailed understanding of how different image features contribute to the model's decisions, offering deeper insights than the traditional approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24117 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Combi-CAM: A Novel Multi-Layer Approach for Explainable Image Geolocalization Faget, David Lisani, José Luis Colom, Miguel Computer Vision and Pattern Recognition Planet-scale photo geolocalization involves the intricate task of estimating the geographic location depicted in an image purely based on its visual features. While deep learning models, particularly convolutional neural networks (CNNs), have significantly advanced this field, understanding the reasoning behind their predictions remains challenging. In this paper, we present Combi-CAM, a novel method that enhances the explainability of CNN-based geolocalization models by combining gradient-weighted class activation maps obtained from several layers of the network architecture, rather than using only information from the deepest layer as is typically done. This approach provides a more detailed understanding of how different image features contribute to the model's decisions, offering deeper insights than the traditional approaches. |
| title | Combi-CAM: A Novel Multi-Layer Approach for Explainable Image Geolocalization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.24117 |