OV-Stitcher: A Global Context-Aware Framework for Training-Free Open-Vocabulary Semantic Segmentation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910118096928768 |
|---|---|
| author | Moon, Seungjae Oh, Seunghyun Ro, Youngmin |
| author_facet | Moon, Seungjae Oh, Seunghyun Ro, Youngmin |
| contents | Training-free open-vocabulary semantic segmentation(TF-OVSS) has recently attracted attention for its ability to perform dense prediction by leveraging the pretrained knowledge of large vision and vision-language models, without requiring additional training. However, due to the limited input resolution of these pretrained encoders, existing TF-OVSS methods commonly adopt a sliding-window strategy that processes cropped sub-images independently. While effective for managing high-resolution inputs, this approach prevents global attention over the full image, leading to fragmented feature representations and limited contextual reasoning. We propose OV-Stitcher, a training-free framework that addresses this limitation by stitching fragmented sub-image features directly within the final encoder block. By reconstructing attention representations from fragmented sub-image features, OV-Stitcher enables global attention within the final encoder block, producing coherent context aggregation and spatially consistent, semantically aligned segmentation maps. Extensive evaluations across eight benchmarks demonstrate that OV-Stitcher establishes a scalable and effective solution for open-vocabulary segmentation, achieving a notable improvement in mean Intersection over Union(mIoU) from 48.7 to 50.7 compared with prior training-free baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08110 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OV-Stitcher: A Global Context-Aware Framework for Training-Free Open-Vocabulary Semantic Segmentation Moon, Seungjae Oh, Seunghyun Ro, Youngmin Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Training-free open-vocabulary semantic segmentation(TF-OVSS) has recently attracted attention for its ability to perform dense prediction by leveraging the pretrained knowledge of large vision and vision-language models, without requiring additional training. However, due to the limited input resolution of these pretrained encoders, existing TF-OVSS methods commonly adopt a sliding-window strategy that processes cropped sub-images independently. While effective for managing high-resolution inputs, this approach prevents global attention over the full image, leading to fragmented feature representations and limited contextual reasoning. We propose OV-Stitcher, a training-free framework that addresses this limitation by stitching fragmented sub-image features directly within the final encoder block. By reconstructing attention representations from fragmented sub-image features, OV-Stitcher enables global attention within the final encoder block, producing coherent context aggregation and spatially consistent, semantically aligned segmentation maps. Extensive evaluations across eight benchmarks demonstrate that OV-Stitcher establishes a scalable and effective solution for open-vocabulary segmentation, achieving a notable improvement in mean Intersection over Union(mIoU) from 48.7 to 50.7 compared with prior training-free baselines. |
| title | OV-Stitcher: A Global Context-Aware Framework for Training-Free Open-Vocabulary Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2604.08110 |