Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916885695561728 |
|---|---|
| author | Choi, Jiho Lee, Seonho Lee, Minhyun Lee, Seungho Shim, Hyunjung |
| author_facet | Choi, Jiho Lee, Seonho Lee, Minhyun Lee, Seungho Shim, Hyunjung |
| contents | Open-Vocabulary Part Segmentation (OVPS) is an emerging field for recognizing fine-grained parts in unseen categories. We identify two primary challenges in OVPS: (1) the difficulty in aligning part-level image-text correspondence, and (2) the lack of structural understanding in segmenting object parts. To address these issues, we propose PartCATSeg, a novel framework that integrates object-aware part-level cost aggregation, compositional loss, and structural guidance from DINO. Our approach employs a disentangled cost aggregation strategy that handles object and part-level costs separately, enhancing the precision of part-level segmentation. We also introduce a compositional loss to better capture part-object relationships, compensating for the limited part annotations. Additionally, structural guidance from DINO features improves boundary delineation and inter-part understanding. Extensive experiments on Pascal-Part-116, ADE20K-Part-234, and PartImageNet datasets demonstrate that our method significantly outperforms state-of-the-art approaches, setting a new baseline for robust generalization to unseen part categories. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_09688 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation Choi, Jiho Lee, Seonho Lee, Minhyun Lee, Seungho Shim, Hyunjung Computer Vision and Pattern Recognition Open-Vocabulary Part Segmentation (OVPS) is an emerging field for recognizing fine-grained parts in unseen categories. We identify two primary challenges in OVPS: (1) the difficulty in aligning part-level image-text correspondence, and (2) the lack of structural understanding in segmenting object parts. To address these issues, we propose PartCATSeg, a novel framework that integrates object-aware part-level cost aggregation, compositional loss, and structural guidance from DINO. Our approach employs a disentangled cost aggregation strategy that handles object and part-level costs separately, enhancing the precision of part-level segmentation. We also introduce a compositional loss to better capture part-object relationships, compensating for the limited part annotations. Additionally, structural guidance from DINO features improves boundary delineation and inter-part understanding. Extensive experiments on Pascal-Part-116, ADE20K-Part-234, and PartImageNet datasets demonstrate that our method significantly outperforms state-of-the-art approaches, setting a new baseline for robust generalization to unseen part categories. |
| title | Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.09688 |