# MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation

arXiv: https://arxiv.org/abs/2503.06700 · HTML: https://mlsanity.com/paper/2503.06700/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 80 references that are in the map.
- First posted on arXiv 9 Mar 2025.

## Builds on (most cited first, 30 of 54)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation](https://mlsanity.com/paper/2004.02147/) (2020)
- [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1606.02147/) (2016)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Fast-SCNN: Fast Semantic Segmentation Network](https://mlsanity.com/paper/1902.04502/) (2019)
- [Robust Classification with Convolutional Prototype Learning](https://mlsanity.com/paper/1805.03438/) (2018)
- [Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation](https://mlsanity.com/paper/2007.09183/) (2020)
- [Delivering Arbitrary-Modal Semantic Segmentation](https://mlsanity.com/paper/2303.01480/) (2023)
- [SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory](https://mlsanity.com/paper/2411.11922/) (2024)
- [Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks](https://mlsanity.com/paper/2302.08890/) (2023)
- [Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis](https://mlsanity.com/paper/2011.06961/) (2020)
- [SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree](https://mlsanity.com/paper/2410.16268/) (2024)
- [ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation](https://mlsanity.com/paper/2108.10528/) (2021)
- [DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation](https://mlsanity.com/paper/2309.09668/) (2023)
- [Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation](https://mlsanity.com/paper/2004.04534/) (2020)
- [FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation](https://mlsanity.com/paper/2110.08988/) (2021)
- [Frame-Event Alignment and Fusion Network for High Frame Rate Tracking](https://mlsanity.com/paper/2305.15688/) (2023)
- [ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data](https://mlsanity.com/paper/2008.08974/) (2020)
- [ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation](https://mlsanity.com/paper/2108.12382/) (2021)
- [Relax Image-Specific Prompt Requirement in SAM: A Single Generic Prompt for Segmenting Camouflaged Objects](https://mlsanity.com/paper/2312.07374/) (2023)

## Built on by (most cited first, 10 of 10)

- [MLLMs are Deeply Affected by Modality Bias](https://mlsanity.com/paper/2505.18657/) (2025)
- [Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness](https://mlsanity.com/paper/2503.18445/) (2025)
- [Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization](https://mlsanity.com/paper/2505.06635/) (2025)
- [PanoEnv: Exploring 3D Spatial Intelligence in Panoramic Environments with Reinforcement Learning](https://mlsanity.com/paper/2602.21992/) (2026)
- [Split Matching for Inductive Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2505.05023/) (2025)
- [EGFormer: Towards Efficient and Generalizable Multimodal Semantic Segmentation](https://mlsanity.com/paper/2505.14014/) (2025)
- [BiXFormer: A Robust Framework for Maximizing Modality Effectiveness in Multi-Modal Semantic Segmentation](https://mlsanity.com/paper/2506.03675/) (2025)
- [Med-K2N: Flexible K-to-N Modality Translation for Medical Image Synthesis](https://mlsanity.com/paper/2510.02815/) (2025)
- [4th Workshop on Maritime Computer Vision (MaCVi): Challenge Overview](https://mlsanity.com/paper/2604.13244/) (2026)
- [Multimodal Fusion of RGB and Complementary Modalities for Semantic Segmentation](https://mlsanity.com/paper/2610.17800/) (2026)

## Abstract (arXiv)

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.