# Learning Robust Anymodal Segmentor with Unimodal and Cross-modal Distillation

arXiv: https://arxiv.org/abs/2411.17141 · HTML: https://mlsanity.com/paper/2411.17141/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 37 references that are in the map.
- First posted on arXiv 26 Nov 2024.

## Builds on (most cited first, 29 of 29)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Balanced Multimodal Learning via On-the-fly Gradient Modulation](https://mlsanity.com/paper/2203.15332/) (2022)
- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [Multimodal Token Fusion for Vision Transformers](https://mlsanity.com/paper/2204.08721/) (2022)
- [Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)](https://mlsanity.com/paper/2203.12221/) (2022)
- [Delivering Arbitrary-Modal Semantic Segmentation](https://mlsanity.com/paper/2303.01480/) (2023)
- [MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving](https://mlsanity.com/paper/2303.08600/) (2023)
- [Multi-Modal 3D Object Detection in Autonomous Driving: a Survey](https://mlsanity.com/paper/2106.12735/) (2021)
- [UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All](https://mlsanity.com/paper/2403.12532/) (2024)
- [Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation](https://mlsanity.com/paper/2004.04534/) (2020)
- [Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2303.14360/) (2023)
- [Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality](https://mlsanity.com/paper/2310.01035/) (2023)
- [MMANet: Margin-aware Distillation and Modality-aware Regularization for Incomplete Multimodal Learning](https://mlsanity.com/paper/2304.08028/) (2023)
- [EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding](https://mlsanity.com/paper/2308.03135/) (2023)
- [Semantics, Distortion, and Style Matter: Towards Source-free UDA for Panoramic Segmentation](https://mlsanity.com/paper/2403.12505/) (2024)
- [MUSES: The Multi-Sensor Semantic Perception Dataset for Driving under Uncertainty](https://mlsanity.com/paper/2401.12761/) (2024)
- [HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection](https://mlsanity.com/paper/2206.15157/) (2022)
- [Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities](https://mlsanity.com/paper/2407.11351/) (2024)
- [Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation](https://mlsanity.com/paper/2310.03986/) (2023)
- [360SFUDA++: Towards Source-free UDA for Panoramic Segmentation by Learning Reliable Category Prototypes](https://mlsanity.com/paper/2404.16501/) (2024)
- [Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation](https://mlsanity.com/paper/2304.10756/) (2023)
- [EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition](https://mlsanity.com/paper/2403.14082/) (2024)
- [Centering the Value of Every Modality: Towards Efficient and Resilient Modality-agnostic Semantic Segmentation](https://mlsanity.com/paper/2407.11344/) (2024)
- [OmniBind: Teach to Build Unequal-Scale Modality Interaction for Omni-Bind of All](https://mlsanity.com/paper/2405.16108/) (2024)
- [Understanding Unimodal Bias in Multimodal Deep Linear Networks](https://mlsanity.com/paper/2312.00935/) (2023)
- [Transformer-CNN Cohort: Semi-supervised Semantic Segmentation by the Best of Both Students](https://mlsanity.com/paper/2209.02178/) (2022)
- [Critical Learning Periods for Multisensory Integration in Deep Networks](https://mlsanity.com/paper/2210.04643/) (2022)
- [Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation](https://mlsanity.com/paper/2401.16923/) (2024)
- [Redundancy-Adaptive Multimodal Learning for Imperfect Data](https://mlsanity.com/paper/2310.14496/) (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)
- [Customize Segment Anything Model for Multi-Modal Semantic Segmentation with Mixture of LoRA Experts](https://mlsanity.com/paper/2412.04220/) (2024)
- [Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization](https://mlsanity.com/paper/2505.06635/) (2025)
- [CIARD: Cyclic Iterative Adversarial Robustness Distillation](https://mlsanity.com/paper/2509.12633/) (2025)
- [SARTM: Segment Any RGB Thermal Model with Language aided Distillation](https://mlsanity.com/paper/2505.01950/) (2025)
- [BiXFormer: A Robust Framework for Maximizing Modality Effectiveness in Multi-Modal Semantic Segmentation](https://mlsanity.com/paper/2506.03675/) (2025)
- [Partial CLIP is Enough: Chimera-Seg for Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2506.22032/) (2025)
- [RTFDNet: Fusion-Decoupling for Robust RGB-T Segmentation](https://mlsanity.com/paper/2603.09149/) (2026)
- [CrossWeaver: Cross-modal Weaving for Arbitrary-Modality Semantic Segmentation](https://mlsanity.com/paper/2604.02948/) (2026)

## Abstract (arXiv)

Simultaneously using multimodal inputs from multiple sensors to train segmentors is intuitively advantageous but practically challenging. A key challenge is unimodal bias, where multimodal segmentors over rely on certain modalities, causing performance drops when others are missing, common in real world applications. To this end, we develop the first framework for learning robust segmentor that can handle any combinations of visual modalities. Specifically, we first introduce a parallel multimodal learning strategy for learning a strong teacher. The cross-modal and unimodal distillation is then achieved in the multi scale representation space by transferring the feature level knowledge from multimodal to anymodal segmentors, aiming at addressing the unimodal bias and avoiding over-reliance on specific modalities. Moreover, a prediction level modality agnostic semantic distillation is proposed to achieve semantic knowledge transferring for segmentation. Extensive experiments on both synthetic and real-world multi-sensor benchmarks demonstrate that our method achieves superior performance.