Animal Identification with Independent Foreground and Background Modeling
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_ | 1866914921429598208 |
|---|---|
| author | Picek, Lukas Neumann, Lukas Matas, Jiri |
| author_facet | Picek, Lukas Neumann, Lukas Matas, Jiri |
| contents | We propose a method that robustly exploits background and foreground in visual identification of individual animals. Experiments show that their automatic separation, made easy with methods like Segment Anything, together with independent foreground and background-related modeling, improves results. The two predictions are combined in a principled way, thanks to novel Per-Instance Temperature Scaling that helps the classifier to deal with appearance ambiguities in training and to produce calibrated outputs in the inference phase. For identity prediction from the background, we propose novel spatial and temporal models. On two problems, the relative error w.r.t. the baseline was reduced by 22.3% and 8.8%, respectively. For cases where objects appear in new locations, an example of background drift, accuracy doubles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12930 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Animal Identification with Independent Foreground and Background Modeling Picek, Lukas Neumann, Lukas Matas, Jiri Computer Vision and Pattern Recognition We propose a method that robustly exploits background and foreground in visual identification of individual animals. Experiments show that their automatic separation, made easy with methods like Segment Anything, together with independent foreground and background-related modeling, improves results. The two predictions are combined in a principled way, thanks to novel Per-Instance Temperature Scaling that helps the classifier to deal with appearance ambiguities in training and to produce calibrated outputs in the inference phase. For identity prediction from the background, we propose novel spatial and temporal models. On two problems, the relative error w.r.t. the baseline was reduced by 22.3% and 8.8%, respectively. For cases where objects appear in new locations, an example of background drift, accuracy doubles. |
| title | Animal Identification with Independent Foreground and Background Modeling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.12930 |