Unified Framework for Open-World Compositional Zero-shot Learning
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_ | 1866913599203573760 |
|---|---|
| author | Jayasekara, Hirunima Pham, Khoi Saini, Nirat Shrivastava, Abhinav |
| author_facet | Jayasekara, Hirunima Pham, Khoi Saini, Nirat Shrivastava, Abhinav |
| contents | Open-World Compositional Zero-Shot Learning (OW-CZSL) addresses the challenge of recognizing novel compositions of known primitives and entities. Even though prior works utilize language knowledge for recognition, such approaches exhibit limited interactions between language-image modalities. Our approach primarily focuses on enhancing the inter-modality interactions through fostering richer interactions between image and textual data. Additionally, we introduce a novel module aimed at alleviating the computational burden associated with exhaustive exploration of all possible compositions during the inference stage. While previous methods exclusively learn compositions jointly or independently, we introduce an advanced hybrid procedure that leverages both learning mechanisms to generate final predictions. Our proposed model, achieves state-of-the-art in OW-CZSL in three datasets, while surpassing Large Vision Language Models (LLVM) in two datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_04083 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unified Framework for Open-World Compositional Zero-shot Learning Jayasekara, Hirunima Pham, Khoi Saini, Nirat Shrivastava, Abhinav Computer Vision and Pattern Recognition Open-World Compositional Zero-Shot Learning (OW-CZSL) addresses the challenge of recognizing novel compositions of known primitives and entities. Even though prior works utilize language knowledge for recognition, such approaches exhibit limited interactions between language-image modalities. Our approach primarily focuses on enhancing the inter-modality interactions through fostering richer interactions between image and textual data. Additionally, we introduce a novel module aimed at alleviating the computational burden associated with exhaustive exploration of all possible compositions during the inference stage. While previous methods exclusively learn compositions jointly or independently, we introduce an advanced hybrid procedure that leverages both learning mechanisms to generate final predictions. Our proposed model, achieves state-of-the-art in OW-CZSL in three datasets, while surpassing Large Vision Language Models (LLVM) in two datasets. |
| title | Unified Framework for Open-World Compositional Zero-shot Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.04083 |