# UMSS: Towards Unsupervised Multi-modal Semantic Segmentation

arXiv: https://arxiv.org/abs/2607.12372 · HTML: https://mlsanity.com/paper/2607.12372/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 53 of its 86 references that are in the map.
- First posted on arXiv 14 Jul 2026.

## Builds on (most cited first, 30 of 53)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018)
- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [A Survey of Autonomous Driving: Common Practices and Emerging Technologies](https://mlsanity.com/paper/1906.05113/) (2019)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [Debiased Contrastive Learning](https://mlsanity.com/paper/2007.00224/) (2020)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Unsupervised Semantic Segmentation by Distilling Feature Correspondences](https://mlsanity.com/paper/2203.08414/) (2022)
- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering](https://mlsanity.com/paper/2103.17070/) (2021)
- [Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation](https://mlsanity.com/paper/2308.02097/) (2023)
- [Delivering Arbitrary-Modal Semantic Segmentation](https://mlsanity.com/paper/2303.01480/) (2023)
- [Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Survey](https://mlsanity.com/paper/2307.04370/) (2023)
- [Unsupervised Learning by Predicting Noise](https://mlsanity.com/paper/1704.05310/) (2017)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting](https://mlsanity.com/paper/2012.04529/) (2020)
- [Cross-modal knowledge distillation for action recognition](https://mlsanity.com/paper/1910.04641/) (2019)
- [Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality](https://mlsanity.com/paper/2310.01035/) (2023)
- [GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer](https://mlsanity.com/paper/2406.01210/) (2024)
- [DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation](https://mlsanity.com/paper/2309.15109/) (2023)

## Abstract (arXiv)

Multimodal semantic segmentation (MSS) is essential for robust perception in complex environments, yet its potential remains largely untapped because of the prohibitive cost of human annotations. While unsupervised semantic segmentation (USS) has achieved strong results on a single RGB modality, its naive extension to multimodal data is often hindered by fusion degradation. This occurs because, without explicit supervision, existing frameworks struggle to reconcile the heterogeneous structural patterns captured by different sensors and therefore fail to effectively exploit their complementary information. In this paper, we make the first attempt to address the novel problem of Unsupervised Multimodal Semantic Segmentation (UMSS), aiming to effectively exploit complementary sensor information in a fully label free setting. To this end, we propose UniM2 (Unified Multimodal), a novel framework built on DINOv3 that transforms conventional fusion methods into consistent performance gains. Our key idea is to learn a unified latent space driven by Cross Modal Correspondence Synergy (CMCS) to extract intrinsic shared semantic cues, bypassing the need for label guided adaptive fusion. To mitigate inherent intermodal conflicts, we introduce a Cross Modal Harmonizer (CMH) that designates RGB as a stable reference, effectively suppressing inconsistent relational supervision while guiding the model to exploit complementary structural features. Extensive experimental results on NYU Depth v2 and MFNet show that UniM2 improves mIoU by 6.4% and 9.8%, respectively, demonstrating clear advantages over existing frameworks for UMSS.