PANICL: Mitigating Over-Reliance on Single Prompt in Visual In-Context 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_ | 1866912607968952320 |
|---|---|
| author | Zhang, Jiahao Wang, Bowen Liu, Hong Nakashima, Yuta Nagahara, Hajime |
| author_facet | Zhang, Jiahao Wang, Bowen Liu, Hong Nakashima, Yuta Nagahara, Hajime |
| contents | Visual In-Context Learning (VICL) uses input-output image pairs, referred to as in-context pairs (or examples), as prompts alongside query images to guide models in performing diverse vision tasks. However, VICL often suffers from over-reliance on a single in-context pair, which can lead to biased and unstable predictions. We introduce PAtch-based $k$-Nearest neighbor visual In-Context Learning (PANICL), a general training-free framework that mitigates this issue by leveraging multiple in-context pairs. PANICL smooths assignment scores across pairs, reducing bias without requiring additional training. Extensive experiments on a variety of tasks, including foreground segmentation, single object detection, colorization, multi-object segmentation, and keypoint detection, demonstrate consistent improvements over strong baselines. Moreover, PANICL exhibits strong robustness to domain shifts, including dataset-level shift (e.g., from COCO to Pascal) and label-space shift (e.g., FSS-1000), and generalizes well to other VICL models such as SegGPT, Painter, and LVM, highlighting its versatility and broad applicability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21926 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PANICL: Mitigating Over-Reliance on Single Prompt in Visual In-Context Learning Zhang, Jiahao Wang, Bowen Liu, Hong Nakashima, Yuta Nagahara, Hajime Computer Vision and Pattern Recognition Visual In-Context Learning (VICL) uses input-output image pairs, referred to as in-context pairs (or examples), as prompts alongside query images to guide models in performing diverse vision tasks. However, VICL often suffers from over-reliance on a single in-context pair, which can lead to biased and unstable predictions. We introduce PAtch-based $k$-Nearest neighbor visual In-Context Learning (PANICL), a general training-free framework that mitigates this issue by leveraging multiple in-context pairs. PANICL smooths assignment scores across pairs, reducing bias without requiring additional training. Extensive experiments on a variety of tasks, including foreground segmentation, single object detection, colorization, multi-object segmentation, and keypoint detection, demonstrate consistent improvements over strong baselines. Moreover, PANICL exhibits strong robustness to domain shifts, including dataset-level shift (e.g., from COCO to Pascal) and label-space shift (e.g., FSS-1000), and generalizes well to other VICL models such as SegGPT, Painter, and LVM, highlighting its versatility and broad applicability. |
| title | PANICL: Mitigating Over-Reliance on Single Prompt in Visual In-Context Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.21926 |