# EGFormer: Towards Efficient and Generalizable Multimodal Semantic Segmentation

arXiv: https://arxiv.org/abs/2505.14014 · HTML: https://mlsanity.com/paper/2505.14014/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 67 references that are in the map.
- First posted on arXiv 20 May 2025.

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

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation](https://mlsanity.com/paper/2209.08575/) (2022)
- [Multimodal Token Fusion for Vision Transformers](https://mlsanity.com/paper/2204.08721/) (2022)
- [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)
- [Strip Pooling: Rethinking Spatial Pooling for Scene Parsing](https://mlsanity.com/paper/2003.13328/) (2020)
- [Boundary-Aware Feature Propagation for Scene Segmentation](https://mlsanity.com/paper/1909.00179/) (2019)
- [SegViT: Semantic Segmentation with Plain Vision Transformers](https://mlsanity.com/paper/2210.05844/) (2022)
- [Improving Semantic Segmentation via Decoupled Body and Edge Supervision](https://mlsanity.com/paper/2007.10035/) (2020)
- [EV-SegNet: Semantic Segmentation for Event-based Cameras](https://mlsanity.com/paper/1811.12039/) (2018)
- [Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation](https://mlsanity.com/paper/2111.01236/) (2021)
- [Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks](https://mlsanity.com/paper/2302.08890/) (2023)
- [ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation](https://mlsanity.com/paper/2108.10528/) (2021)
- [Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks](https://mlsanity.com/paper/2003.05128/) (2020)
- [MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving](https://mlsanity.com/paper/2303.08600/) (2023)
- [InverseForm: A Loss Function for Structured Boundary-Aware Segmentation](https://mlsanity.com/paper/2104.02745/) (2021)
- [Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks](https://mlsanity.com/paper/1711.08681/) (2017)
- [Multi-shot Temporal Event Localization: a Benchmark](https://mlsanity.com/paper/2012.09434/) (2020)
- [UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All](https://mlsanity.com/paper/2403.12532/) (2024)
- [Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2303.14360/) (2023)

## Built on by (most cited first, 1 of 1)

- [CrossWeaver: Cross-modal Weaving for Arbitrary-Modality Semantic Segmentation](https://mlsanity.com/paper/2604.02948/) (2026)

## Abstract (arXiv)

Recent efforts have explored multimodal semantic segmentation using various backbone architectures. However, while most methods aim to improve accuracy, their computational efficiency remains underexplored. To address this, we propose EGFormer, an efficient multimodal semantic segmentation framework that flexibly integrates an arbitrary number of modalities while significantly reducing model parameters and inference time without sacrificing performance. Our framework introduces two novel modules. First, the Any-modal Scoring Module (ASM) assigns importance scores to each modality independently, enabling dynamic ranking based on their feature maps. Second, the Modal Dropping Module (MDM) filters out less informative modalities at each stage, selectively preserving and aggregating only the most valuable features. This design allows the model to leverage useful information from all available modalities while discarding redundancy, thus ensuring high segmentation quality. In addition to efficiency, we evaluate EGFormer on a synthetic-to-real transfer task to demonstrate its generalizability. Extensive experiments show that EGFormer achieves competitive performance with up to 88 percent reduction in parameters and 50 percent fewer GFLOPs. Under unsupervised domain adaptation settings, it further achieves state-of-the-art transfer performance compared to existing methods.