Learning Primitive Relations for Compositional Zero-Shot Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915119896723456 |
|---|---|
| author | Lee, Insu Kim, Jiseob Shim, Kyuhong Shim, Byonghyo |
| author_facet | Lee, Insu Kim, Jiseob Shim, Kyuhong Shim, Byonghyo |
| contents | Compositional Zero-Shot Learning (CZSL) aims to identify unseen state-object compositions by leveraging knowledge learned from seen compositions. Existing approaches often independently predict states and objects, overlooking their relationships. In this paper, we propose a novel framework, learning primitive relations (LPR), designed to probabilistically capture the relationships between states and objects. By employing the cross-attention mechanism, LPR considers the dependencies between states and objects, enabling the model to infer the likelihood of unseen compositions. Experimental results demonstrate that LPR outperforms state-of-the-art methods on all three CZSL benchmark datasets in both closed-world and open-world settings. Through qualitative analysis, we show that LPR leverages state-object relationships for unseen composition prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_14308 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Primitive Relations for Compositional Zero-Shot Learning Lee, Insu Kim, Jiseob Shim, Kyuhong Shim, Byonghyo Computer Vision and Pattern Recognition Artificial Intelligence Compositional Zero-Shot Learning (CZSL) aims to identify unseen state-object compositions by leveraging knowledge learned from seen compositions. Existing approaches often independently predict states and objects, overlooking their relationships. In this paper, we propose a novel framework, learning primitive relations (LPR), designed to probabilistically capture the relationships between states and objects. By employing the cross-attention mechanism, LPR considers the dependencies between states and objects, enabling the model to infer the likelihood of unseen compositions. Experimental results demonstrate that LPR outperforms state-of-the-art methods on all three CZSL benchmark datasets in both closed-world and open-world settings. Through qualitative analysis, we show that LPR leverages state-object relationships for unseen composition prediction. |
| title | Learning Primitive Relations for Compositional Zero-Shot Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2501.14308 |