Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2406.05120 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916279673159680 |
|---|---|
| author | Joshi, Shruti Akumalla, Aiswarya Haney, Seth Bazhenov, Maxim |
| author_facet | Joshi, Shruti Akumalla, Aiswarya Haney, Seth Bazhenov, Maxim |
| contents | Mammalian brains handle complex reasoning by integrating information across brain regions specialized for particular sensory modalities. This enables improved robustness and generalization versus deep neural networks, which typically process one modality and are vulnerable to perturbations. While defense methods exist, they do not generalize well across perturbations. We developed a fusion model combining background and foreground features from CNNs trained on Imagenet and Places365. We tested its robustness to human-perceivable perturbations on MS COCO. The fusion model improved robustness, especially for classes with greater context variability. Our proposed solution for integrating multiple modalities provides a new approach to enhance robustness and may be complementary to existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_05120 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Contextual fusion enhances robustness to image blurring Joshi, Shruti Akumalla, Aiswarya Haney, Seth Bazhenov, Maxim Computer Vision and Pattern Recognition Mammalian brains handle complex reasoning by integrating information across brain regions specialized for particular sensory modalities. This enables improved robustness and generalization versus deep neural networks, which typically process one modality and are vulnerable to perturbations. While defense methods exist, they do not generalize well across perturbations. We developed a fusion model combining background and foreground features from CNNs trained on Imagenet and Places365. We tested its robustness to human-perceivable perturbations on MS COCO. The fusion model improved robustness, especially for classes with greater context variability. Our proposed solution for integrating multiple modalities provides a new approach to enhance robustness and may be complementary to existing methods. |
| title | Contextual fusion enhances robustness to image blurring |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.05120 |