English(EN) SARTM: Segment Any RGB Thermal Model with Language aided Distillation

新的SARTM框架将SAM适配于RGB-热力学分割

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-02 04:00

研究人员开发了SARTM，一个旨在将分割任何模型（SAM）适配于RGB-热力学（RGB-T）语义分割的新框架。SARTM使用LoRA层对SAM进行微调，并通过跨模态知识蒸馏（CMKD）引入语言指导，以解决跨模态不一致和语义模糊问题。该框架还通过调整SAM的头部和集成多尺度特征来增强分割效果。在MFNET、PST900和FMB等基准测试上的实验表明，SARTM的性能优于现有的最先进方法。 AI

影响增强了RGB-热力学数据的计算机视觉能力，有可能在挑战性条件下改善场景理解。

排序理由这是一篇详细介绍新模型和方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 27 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍新模型和方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Dong Xing, Jinhe Zhang, Hang Yang, Yuqing Wang · 2026-09-02 04:00

SARTM：通过语言辅助蒸馏分割任何RGB热模型

arXiv:2505.01950v2 Announce Type: replace-cross 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 (R…

本文如何被排名

报道来源 [1]

SARTM：通过语言辅助蒸馏分割任何RGB热模型

相关实体

相关话题