KAN-SAM: Kolmogorov-Arnold Network Guided Segment Anything Model for RGB-T Salient Object Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916678901694464 |
|---|---|
| author | Li, Xingyuan Hou, Ruichao Ren, Tongwei Wu, Gangshan |
| author_facet | Li, Xingyuan Hou, Ruichao Ren, Tongwei Wu, Gangshan |
| contents | Existing RGB-thermal salient object detection (RGB-T SOD) methods aim to identify visually significant objects by leveraging both RGB and thermal modalities to enable robust performance in complex scenarios, but they often suffer from limited generalization due to the constrained diversity of available datasets and the inefficiencies in constructing multi-modal representations. In this paper, we propose a novel prompt learning-based RGB-T SOD method, named KAN-SAM, which reveals the potential of visual foundational models for RGB-T SOD tasks. Specifically, we extend Segment Anything Model 2 (SAM2) for RGB-T SOD by introducing thermal features as guiding prompts through efficient and accurate Kolmogorov-Arnold Network (KAN) adapters, which effectively enhance RGB representations and improve robustness. Furthermore, we introduce a mutually exclusive random masking strategy to reduce reliance on RGB data and improve generalization. Experimental results on benchmarks demonstrate superior performance over the state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05878 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KAN-SAM: Kolmogorov-Arnold Network Guided Segment Anything Model for RGB-T Salient Object Detection Li, Xingyuan Hou, Ruichao Ren, Tongwei Wu, Gangshan Multimedia Computer Vision and Pattern Recognition Existing RGB-thermal salient object detection (RGB-T SOD) methods aim to identify visually significant objects by leveraging both RGB and thermal modalities to enable robust performance in complex scenarios, but they often suffer from limited generalization due to the constrained diversity of available datasets and the inefficiencies in constructing multi-modal representations. In this paper, we propose a novel prompt learning-based RGB-T SOD method, named KAN-SAM, which reveals the potential of visual foundational models for RGB-T SOD tasks. Specifically, we extend Segment Anything Model 2 (SAM2) for RGB-T SOD by introducing thermal features as guiding prompts through efficient and accurate Kolmogorov-Arnold Network (KAN) adapters, which effectively enhance RGB representations and improve robustness. Furthermore, we introduce a mutually exclusive random masking strategy to reduce reliance on RGB data and improve generalization. Experimental results on benchmarks demonstrate superior performance over the state-of-the-art methods. |
| title | KAN-SAM: Kolmogorov-Arnold Network Guided Segment Anything Model for RGB-T Salient Object Detection |
| topic | Multimedia Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.05878 |