# MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation Source: [MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:05:43.357Z Authors: Chenfei Liao, Xu Zheng, Yuanhuiyi Lyu, Haiwei Xue, Yihong Cao, Jiawen Wang, Kailun Yang, Xuming Hu Published: 2025-03-09T17:33:15.000Z ## Abstract Research has focused on Multi-Modal Semantic Segmentation (MMSS), where pixel-wise predictions are derived from multiple visual modalities captured by diverse sensors. Recently, the large vision model, Segment Anything Model 2 (SAM2), has shown strong zero-shot segmentation performance on both images and videos. When extending SAM2 to MMSS, two issues arise: 1. How can SAM2 be adapted to multi-modal data? 2. How can SAM2 better understand semantics? Inspired by cross-frame correlation in videos, we propose to treat multi-modal data as a sequence of frames representing the same scene. Our key idea is to ''memorize'' the modality-agnostic information and 'memorize' the semantics related to the targeted scene. To achieve this, we apply SAM2's memory mechanisms across multi-modal data to capture modality-agnostic features. Meanwhile, to memorize the semantic knowledge, we propose a training-only Semantic Prototype Memory Module (SPMM) to store category-level prototypes across training for facilitating SAM2's transition from instance to semantic segmentation. A prototypical adaptation loss is imposed between global and local prototypes iteratively to align and refine SAM2's semantic understanding. Extensive experimental results demonstrate that our proposed MemorySAM outperforms SoTA methods by large margins on both synthetic and real-world benchmarks (65.38% on DELIVER, 52.88% on MCubeS). Source code will be made publicly available. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Semantic Segmentation on DELIVER R-D-E-L (test)](): Semantic segmentation; DELIVER R-D-E-L (test); mIoU: 65.38. - [Material Segmentation on MCubeS (test)](): Material Segmentation; MCubeS (test); mIoU: 52.88. - [Semantic Segmentation on DELIVER RGB (test)](): Semantic segmentation; DELIVER RGB (test); mIoU: 53.22. - [Semantic Segmentation on DELIVER R-D (test)](): Semantic segmentation; DELIVER R-D (test); mIoU: 63.48. - [Semantic Segmentation on DELIVER R-D-E (test)](): Semantic segmentation; DELIVER R-D-E (test); mIoU: 62.42. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()