{"ID":2865074,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21926","arxiv_id":"2509.21926","title":"PANICL: Mitigating Over-Reliance on Single Prompt in Visual In-Context Learning","abstract":"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.","short_abstract":"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 predicti...","url_abs":"https://arxiv.org/abs/2509.21926","url_pdf":"https://arxiv.org/pdf/2509.21926v1","authors":"[\"Jiahao Zhang\",\"Bowen Wang\",\"Hong Liu\",\"Yuta Nakashima\",\"Hajime Nagahara\"]","published":"2025-09-26T06:13:40Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}