Explorations in Texture Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914714666139648 |
|---|---|
| author | Hoak, Blaine McDaniel, Patrick |
| author_facet | Hoak, Blaine McDaniel, Patrick |
| contents | In this work, we investigate \textit{texture learning}: the identification of textures learned by object classification models, and the extent to which they rely on these textures. We build texture-object associations that uncover new insights about the relationships between texture and object classes in CNNs and find three classes of results: associations that are strong and expected, strong and not expected, and expected but not present. Our analysis demonstrates that investigations in texture learning enable new methods for interpretability and have the potential to uncover unexpected biases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_09543 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Explorations in Texture Learning Hoak, Blaine McDaniel, Patrick Computer Vision and Pattern Recognition Machine Learning In this work, we investigate \textit{texture learning}: the identification of textures learned by object classification models, and the extent to which they rely on these textures. We build texture-object associations that uncover new insights about the relationships between texture and object classes in CNNs and find three classes of results: associations that are strong and expected, strong and not expected, and expected but not present. Our analysis demonstrates that investigations in texture learning enable new methods for interpretability and have the potential to uncover unexpected biases. |
| title | Explorations in Texture Learning |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2403.09543 |