Segmenting Object Affordances: Reproducibility and Sensitivity to Scale
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_ | 1866918032596533248 |
|---|---|
| author | Apicella, Tommaso Xompero, Alessio Gastaldo, Paolo Cavallaro, Andrea |
| author_facet | Apicella, Tommaso Xompero, Alessio Gastaldo, Paolo Cavallaro, Andrea |
| contents | Visual affordance segmentation identifies image regions of an object an agent can interact with. Existing methods re-use and adapt learning-based architectures for semantic segmentation to the affordance segmentation task and evaluate on small-size datasets. However, experimental setups are often not reproducible, thus leading to unfair and inconsistent comparisons. In this work, we benchmark these methods under a reproducible setup on two single objects scenarios, tabletop without occlusions and hand-held containers, to facilitate future comparisons. We include a version of a recent architecture, Mask2Former, re-trained for affordance segmentation and show that this model is the best-performing on most testing sets of both scenarios. Our analysis shows that models are not robust to scale variations when object resolutions differ from those in the training set. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_01814 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Segmenting Object Affordances: Reproducibility and Sensitivity to Scale Apicella, Tommaso Xompero, Alessio Gastaldo, Paolo Cavallaro, Andrea Computer Vision and Pattern Recognition Visual affordance segmentation identifies image regions of an object an agent can interact with. Existing methods re-use and adapt learning-based architectures for semantic segmentation to the affordance segmentation task and evaluate on small-size datasets. However, experimental setups are often not reproducible, thus leading to unfair and inconsistent comparisons. In this work, we benchmark these methods under a reproducible setup on two single objects scenarios, tabletop without occlusions and hand-held containers, to facilitate future comparisons. We include a version of a recent architecture, Mask2Former, re-trained for affordance segmentation and show that this model is the best-performing on most testing sets of both scenarios. Our analysis shows that models are not robust to scale variations when object resolutions differ from those in the training set. |
| title | Segmenting Object Affordances: Reproducibility and Sensitivity to Scale |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.01814 |