Segment Any RGB-Thermal Model with Language-aided Distillation

• URL: http://arxiv.org/abs/2505.01950v1
• Date: Sun, 04 May 2025 00:24:17 GMT
• Title: Segment Any RGB-Thermal Model with Language-aided Distillation
• Authors: Dong Xing, Xianxun Zhu, Wei Zhou, Qika Lin, Hang Yang, Yuqing Wang,
• Abstract summary: We propose a novel framework, SARTM, which customizes the powerful SAM for RGB-T semantic segmentation.<n>Our key idea is to unleash the potential of SAM while introduce semantic understanding modules for RGB-T data pairs.<n>Both quantitative and qualitative results consistently demonstrate that the proposed SARTM significantly outperforms state-of-the-art approaches.
• Score: 17.837670087342456
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The recent Segment Anything Model (SAM) demonstrates strong instance segmentation performance across various downstream tasks. However, SAM is trained solely on RGB data, limiting its direct applicability to RGB-thermal (RGB-T) semantic segmentation. Given that RGB-T provides a robust solution for scene understanding in adverse weather and lighting conditions, such as low light and overexposure, we propose a novel framework, SARTM, which customizes the powerful SAM for RGB-T semantic segmentation. Our key idea is to unleash the potential of SAM while introduce semantic understanding modules for RGB-T data pairs. Specifically, our framework first involves fine tuning the original SAM by adding extra LoRA layers, aiming at preserving SAM's strong generalization and segmentation capabilities for downstream tasks. Secondly, we introduce language information as guidance for training our SARTM. To address cross-modal inconsistencies, we introduce a Cross-Modal Knowledge Distillation(CMKD) module that effectively achieves modality adaptation while maintaining its generalization capabilities. This semantic module enables the minimization of modality gaps and alleviates semantic ambiguity, facilitating the combination of any modality under any visual conditions. Furthermore, we enhance the segmentation performance by adjusting the segmentation head of SAM and incorporating an auxiliary semantic segmentation head, which integrates multi-scale features for effective fusion. Extensive experiments are conducted across three multi-modal RGBT semantic segmentation benchmarks: MFNET, PST900, and FMB. Both quantitative and qualitative results consistently demonstrate that the proposed SARTM significantly outperforms state-of-the-art approaches across a variety of conditions.

Related papers

• TASeg: Text-aware RGB-T Semantic Segmentation based on Fine-tuning Vision Foundation Models [26.983562312613877]
  We propose a text-aware RGB-T segmentation framework by using Low-Rank Adaptation (LoRA) fine-tuning technology to adapt vision foundation models.<n>Specifically, we propose a Dynamic Feature Fusion Module (DFFM) in the image encoder, which effectively merges features from multiple visual modalities while freezing SAM's original transformer blocks.
  arXiv  Detail & Related papers  (2025-06-27T07:34:28Z)
• KAN-SAM: Kolmogorov-Arnold Network Guided Segment Anything Model for RGB-T Salient Object Detection [35.52055285209549]
  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.<n>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.<n>We also introduce a mutually exclusive random masking strategy to reduce reliance on RGB data and improve generalization.
  arXiv  Detail & Related papers  (2025-04-08T10:07:02Z)
• Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance [20.104169359248232]
  We propose a novel SAM2-driven Hybrid Interaction Paradigm that unlocks the potential of SAM2 with linguistic guidance for efficient RGB-Thermal perception.<n>SHIFNet achieves state-of-the-art segmentation performance on public benchmarks, reaching 89.8% on PST900 and 67.8% on FMB.
  arXiv  Detail & Related papers  (2025-03-04T13:04:46Z)
• Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond [52.486290612938895]
  We propose a novel method that leverages the semantic knowledge from the Segment Anything Model (SAM) to Grow the quality of fusion results and Enable downstream task adaptability.<n> Specifically, we design a Semantic Persistent Attention (SPA) Module that efficiently maintains source information via the persistent repository while extracting high-level semantic priors from SAM.<n>Our method achieves a balance between high-quality visual results and downstream task adaptability while maintaining practical deployment efficiency.
  arXiv  Detail & Related papers  (2025-03-03T06:16:31Z)
• Customize Segment Anything Model for Multi-Modal Semantic Segmentation with Mixture of LoRA Experts [17.6980007370549]
  We make the first attempt to adapt Segment Anything Model (SAM) for multi-modal semantic segmentation.<n>By training only the MoE-LoRA layers while keeping SAM's weights frozen, SAM's strong generalization and segmentation capabilities can be preserved for downstream tasks.<n>Specifically, to address cross-modal inconsistencies, we propose a novel MoE routing strategy that adaptively generates weighted features across modalities.
  arXiv  Detail & Related papers  (2024-12-05T14:54:31Z)
• Segment Anything with Multiple Modalities [61.74214237816402]
  We develop MM-SAM, which supports cross-modal and multi-modal processing for robust and enhanced segmentation with different sensor suites. MM-SAM features two key designs, namely, unsupervised cross-modal transfer and weakly-supervised multi-modal fusion. It addresses three main challenges: 1) adaptation toward diverse non-RGB sensors for single-modal processing, 2) synergistic processing of multi-modal data via sensor fusion, and 3) mask-free training for different downstream tasks.
  arXiv  Detail & Related papers  (2024-08-17T03:45:40Z)
• AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning [61.666973416903005]
  Segment Anything Model (SAM) has demonstrated its impressive generalization capabilities in open-world scenarios with the guidance of prompts. We propose a novel framework, termed AlignSAM, designed for automatic prompting for aligning SAM to an open context.
  arXiv  Detail & Related papers  (2024-06-01T16:21:39Z)
• SAM-Assisted Remote Sensing Imagery Semantic Segmentation with Object and Boundary Constraints [9.238103649037951]
  We present a framework aimed at leveraging the raw output of SAM by exploiting two novel concepts called SAM-Generated Object (SGO) and SAM-Generated Boundary (SGB) Taking into account the content characteristics of SGO, we introduce the concept of object consistency to leverage segmented regions lacking semantic information. The boundary loss capitalizes on the distinctive features of SGB by directing the model's attention to the boundary information of the object.
  arXiv  Detail & Related papers  (2023-12-05T03:33:47Z)
• Stable Segment Anything Model [79.9005670886038]
  The Segment Anything Model (SAM) achieves remarkable promptable segmentation given high-quality prompts. This paper presents the first comprehensive analysis on SAM's segmentation stability across a diverse spectrum of prompt qualities. Our solution, termed Stable-SAM, offers several advantages: 1) improved SAM's segmentation stability across a wide range of prompt qualities, while 2) retaining SAM's powerful promptable segmentation efficiency and generality.
  arXiv  Detail & Related papers  (2023-11-27T12:51:42Z)
• RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation [53.4319652364256]
  This paper presents the RefSAM model, which explores the potential of SAM for referring video object segmentation. Our proposed approach adapts the original SAM model to enhance cross-modality learning by employing a lightweight Cross-RValModal. We employ a parameter-efficient tuning strategy to align and fuse the language and vision features effectively.
  arXiv  Detail & Related papers  (2023-07-03T13:21:58Z)
• Complementary Random Masking for RGB-Thermal Semantic Segmentation [63.93784265195356]
  RGB-thermal semantic segmentation is a potential solution to achieve reliable semantic scene understanding in adverse weather and lighting conditions. This paper proposes 1) a complementary random masking strategy of RGB-T images and 2) self-distillation loss between clean and masked input modalities. We achieve state-of-the-art performance over three RGB-T semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2023-03-30T13:57:21Z)
• RGB-D Salient Object Detection with Cross-Modality Modulation and Selection [126.4462739820643]
  We present an effective method to progressively integrate and refine the cross-modality complementarities for RGB-D salient object detection (SOD) The proposed network mainly solves two challenging issues: 1) how to effectively integrate the complementary information from RGB image and its corresponding depth map, and 2) how to adaptively select more saliency-related features.
  arXiv  Detail & Related papers  (2020-07-14T14:22:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.