Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2504.15650 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909752053727232 |
|---|---|
| author | Jiang, Dengyang Wang, Zanyi Li, Hengzhuang Dang, Sizhe Ma, Teli Wei, Wei Dai, Guang Zhang, Lei Wang, Mengmeng |
| author_facet | Jiang, Dengyang Wang, Zanyi Li, Hengzhuang Dang, Sizhe Ma, Teli Wei, Wei Dai, Guang Zhang, Lei Wang, Mengmeng |
| contents | Building a generalized affordance grounding model to identify actionable regions on objects is vital for real-world applications. Existing methods to train the model can be divided into weakly and fully supervised ways. However, the former method requires a complex training framework design and can not infer new actions without an auxiliary prior. While the latter often struggle with limited annotated data and components trained from scratch despite being simpler. This study focuses on fully supervised affordance grounding and overcomes its limitations by proposing AffordanceSAM, which extends SAM's generalization capacity in segmentation to affordance grounding. Specifically, we design an affordance-adaption module and curate a coarse-to-fine annotated dataset called C2F-Aff to thoroughly transfer SAM's robust performance to affordance in a three-stage training manner. Experimental results confirm that AffordanceSAM achieves state-of-the-art (SOTA) performance on the AGD20K benchmark and exhibits strong generalized capacity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15650 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AffordanceSAM: Segment Anything Once More in Affordance Grounding Jiang, Dengyang Wang, Zanyi Li, Hengzhuang Dang, Sizhe Ma, Teli Wei, Wei Dai, Guang Zhang, Lei Wang, Mengmeng Computer Vision and Pattern Recognition Building a generalized affordance grounding model to identify actionable regions on objects is vital for real-world applications. Existing methods to train the model can be divided into weakly and fully supervised ways. However, the former method requires a complex training framework design and can not infer new actions without an auxiliary prior. While the latter often struggle with limited annotated data and components trained from scratch despite being simpler. This study focuses on fully supervised affordance grounding and overcomes its limitations by proposing AffordanceSAM, which extends SAM's generalization capacity in segmentation to affordance grounding. Specifically, we design an affordance-adaption module and curate a coarse-to-fine annotated dataset called C2F-Aff to thoroughly transfer SAM's robust performance to affordance in a three-stage training manner. Experimental results confirm that AffordanceSAM achieves state-of-the-art (SOTA) performance on the AGD20K benchmark and exhibits strong generalized capacity. |
| title | AffordanceSAM: Segment Anything Once More in Affordance Grounding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.15650 |