Enhancing Visual In-Context Learning by Multi-Faceted Fusion
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918290335465472 |
|---|---|
| author | Liao, Wenwen Yu, Jianbo Wang, Yuansong Jiang, Qingchao Yang, Xiaofeng |
| author_facet | Liao, Wenwen Yu, Jianbo Wang, Yuansong Jiang, Qingchao Yang, Xiaofeng |
| contents | Visual In-Context Learning (VICL) has emerged as a powerful paradigm, enabling models to perform novel visual tasks by learning from in-context examples. The dominant "retrieve-then-prompt" approach typically relies on selecting the single best visual prompt, a practice that often discards valuable contextual information from other suitable candidates. While recent work has explored fusing the top-K prompts into a single, enhanced representation, this still simply collapses multiple rich signals into one, limiting the model's reasoning capability. We argue that a more multi-faceted, collaborative fusion is required to unlock the full potential of these diverse contexts. To address this limitation, we introduce a novel framework that moves beyond single-prompt fusion towards an multi-combination collaborative fusion. Instead of collapsing multiple prompts into one, our method generates three contextual representation branches, each formed by integrating information from different combinations of top-quality prompts. These complementary guidance signals are then fed into proposed MULTI-VQGAN architecture, which is designed to jointly interpret and utilize collaborative information from multiple sources. Extensive experiments on diverse tasks, including foreground segmentation, single-object detection, and image colorization, highlight its strong cross-task generalization, effective contextual fusion, and ability to produce more robust and accurate predictions than existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_10107 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Enhancing Visual In-Context Learning by Multi-Faceted Fusion Liao, Wenwen Yu, Jianbo Wang, Yuansong Jiang, Qingchao Yang, Xiaofeng Computer Vision and Pattern Recognition Visual In-Context Learning (VICL) has emerged as a powerful paradigm, enabling models to perform novel visual tasks by learning from in-context examples. The dominant "retrieve-then-prompt" approach typically relies on selecting the single best visual prompt, a practice that often discards valuable contextual information from other suitable candidates. While recent work has explored fusing the top-K prompts into a single, enhanced representation, this still simply collapses multiple rich signals into one, limiting the model's reasoning capability. We argue that a more multi-faceted, collaborative fusion is required to unlock the full potential of these diverse contexts. To address this limitation, we introduce a novel framework that moves beyond single-prompt fusion towards an multi-combination collaborative fusion. Instead of collapsing multiple prompts into one, our method generates three contextual representation branches, each formed by integrating information from different combinations of top-quality prompts. These complementary guidance signals are then fed into proposed MULTI-VQGAN architecture, which is designed to jointly interpret and utilize collaborative information from multiple sources. Extensive experiments on diverse tasks, including foreground segmentation, single-object detection, and image colorization, highlight its strong cross-task generalization, effective contextual fusion, and ability to produce more robust and accurate predictions than existing methods. |
| title | Enhancing Visual In-Context Learning by Multi-Faceted Fusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.10107 |