Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance
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_ | 1866912495666462720 |
|---|---|
| author | Zhao, Jiayi Teng, Fei Luo, Kai Zhao, Guoqiang Li, Zhiyong Zheng, Xu Yang, Kailun |
| author_facet | Zhao, Jiayi Teng, Fei Luo, Kai Zhao, Guoqiang Li, Zhiyong Zheng, Xu Yang, Kailun |
| contents | The perception capability of robotic systems relies on the richness of the dataset. Although Segment Anything Model 2 (SAM2), trained on large datasets, demonstrates strong perception potential in perception tasks, its inherent training paradigm prevents it from being suitable for RGB-T tasks. To address these challenges, we propose SHIFNet, a novel SAM2-driven Hybrid Interaction Paradigm that unlocks the potential of SAM2 with linguistic guidance for efficient RGB-Thermal perception. Our framework consists of two key components: (1) Semantic-Aware Cross-modal Fusion (SACF) module that dynamically balances modality contributions through text-guided affinity learning, overcoming SAM2's inherent RGB bias; (2) Heterogeneous Prompting Decoder (HPD) that enhances global semantic information through a semantic enhancement module and then combined with category embeddings to amplify cross-modal semantic consistency. With 32.27M trainable parameters, SHIFNet achieves state-of-the-art segmentation performance on public benchmarks, reaching 89.8% on PST900 and 67.8% on FMB, respectively. The framework facilitates the adaptation of pre-trained large models to RGB-T segmentation tasks, effectively mitigating the high costs associated with data collection while endowing robotic systems with comprehensive perception capabilities. The source code will be made publicly available at https://github.com/iAsakiT3T/SHIFNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02581 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance Zhao, Jiayi Teng, Fei Luo, Kai Zhao, Guoqiang Li, Zhiyong Zheng, Xu Yang, Kailun Computer Vision and Pattern Recognition Robotics Image and Video Processing The perception capability of robotic systems relies on the richness of the dataset. Although Segment Anything Model 2 (SAM2), trained on large datasets, demonstrates strong perception potential in perception tasks, its inherent training paradigm prevents it from being suitable for RGB-T tasks. To address these challenges, we propose SHIFNet, a novel SAM2-driven Hybrid Interaction Paradigm that unlocks the potential of SAM2 with linguistic guidance for efficient RGB-Thermal perception. Our framework consists of two key components: (1) Semantic-Aware Cross-modal Fusion (SACF) module that dynamically balances modality contributions through text-guided affinity learning, overcoming SAM2's inherent RGB bias; (2) Heterogeneous Prompting Decoder (HPD) that enhances global semantic information through a semantic enhancement module and then combined with category embeddings to amplify cross-modal semantic consistency. With 32.27M trainable parameters, SHIFNet achieves state-of-the-art segmentation performance on public benchmarks, reaching 89.8% on PST900 and 67.8% on FMB, respectively. The framework facilitates the adaptation of pre-trained large models to RGB-T segmentation tasks, effectively mitigating the high costs associated with data collection while endowing robotic systems with comprehensive perception capabilities. The source code will be made publicly available at https://github.com/iAsakiT3T/SHIFNet. |
| title | Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance |
| topic | Computer Vision and Pattern Recognition Robotics Image and Video Processing |
| url | https://arxiv.org/abs/2503.02581 |