# AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation

arXiv: https://arxiv.org/abs/2309.14065 · HTML: https://mlsanity.com/paper/2309.14065/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 51 references that are in the map.
- First posted on arXiv 25 Sep 2023.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [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)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation](https://mlsanity.com/paper/2004.02147/) (2020)
- [MultiMAE: Multi-modal Multi-task Masked Autoencoders](https://mlsanity.com/paper/2204.01678/) (2022)
- [Coordinate Attention for Efficient Mobile Network Design](https://mlsanity.com/paper/2103.02907/) (2021)
- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [Omnivore: A Single Model for Many Visual Modalities](https://mlsanity.com/paper/2201.08377/) (2022)
- [ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks](https://mlsanity.com/paper/1908.03930/) (2019)
- [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)
- [ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation](https://mlsanity.com/paper/1905.10089/) (2019)
- [Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis](https://mlsanity.com/paper/2011.06961/) (2020)
- [Temporally Distributed Networks for Fast Video Semantic Segmentation](https://mlsanity.com/paper/2004.01800/) (2020)
- [ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation](https://mlsanity.com/paper/2108.10528/) (2021)
- [RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation](https://mlsanity.com/paper/1806.01054/) (2018)
- [Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios](https://mlsanity.com/paper/2207.05501/) (2022)
- [DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation](https://mlsanity.com/paper/2309.09668/) (2023)

## Built on by (most cited first, 17 of 17)

- [DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation](https://mlsanity.com/paper/2504.04701/) (2025)
- [HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion](https://mlsanity.com/paper/2404.03527/) (2024)
- [Stronger, Steadier & Superior: Geometric Consistency in Depth VFM Forges Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2504.12753/) (2025)
- [RT-GS2: Real-Time Generalizable Semantic Segmentation for 3D Gaussian Representations of Radiance Fields](https://mlsanity.com/paper/2405.18033/) (2024)
- [Cross-Modal Interactive Perception Network with Mamba for Lung Tumor Segmentation in PET-CT Images](https://mlsanity.com/paper/2503.17261/) (2025)
- [LuSeg: Efficient Negative and Positive Obstacles Segmentation via Contrast-Driven Multi-Modal Feature Fusion on the Lunar](https://mlsanity.com/paper/2503.11409/) (2025)
- [Propagating Sparse Depth via Depth Foundation Model for Out-of-Distribution Depth Completion](https://mlsanity.com/paper/2508.04984/) (2025)
- [DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation](https://mlsanity.com/paper/2511.13047/) (2025)
- [Self-supervised cost of transport estimation for multimodal path planning](https://mlsanity.com/paper/2412.06101/) (2024)
- [HDBFormer: Efficient RGB-D Semantic Segmentation with A Heterogeneous Dual-Branch Framework](https://mlsanity.com/paper/2504.13579/) (2025)
- [GeomPrompt: Geometric Prompt Learning for RGB-D Semantic Segmentation Under Missing and Degraded Depth](https://mlsanity.com/paper/2604.11585/) (2026)
- [RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings](https://mlsanity.com/paper/2605.10706/) (2026)
- [NoContactNoWorries: Estimating Contact through Vision and Proprioception for In-Hand Dexterous Manipulation](https://mlsanity.com/paper/2606.24450/) (2026)
- [Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout](https://mlsanity.com/paper/2607.20326/) (2026)
- [URNet: A Unified Reparameterized Network for Efficient RGB-D Semantic Segmentation](https://mlsanity.com/paper/2608.05671/) (2026)
- [A Critical Synthesis of Uncertainty Quantification and Foundation Models for Semantic Segmentation](https://mlsanity.com/paper/2608.18709/) (2026)
- [DTFormer: Text-Guided Semantic Alignment for RGB-D Segmentation](https://mlsanity.com/paper/2610.07014/) (2026)

## Abstract (arXiv)

Understanding indoor scenes is crucial for urban studies. Considering the dynamic nature of indoor environments, effective semantic segmentation requires both real-time operation and high accuracy.To address this, we propose AsymFormer, a novel network that improves real-time semantic segmentation accuracy using RGB-D multi-modal information without substantially increasing network complexity. AsymFormer uses an asymmetrical backbone for multimodal feature extraction, reducing redundant parameters by optimizing computational resource distribution. To fuse asymmetric multimodal features, a Local Attention-Guided Feature Selection (LAFS) module is used to selectively fuse features from different modalities by leveraging their dependencies. Subsequently, a Cross-Modal Attention-Guided Feature Correlation Embedding (CMA) module is introduced to further extract cross-modal representations. The AsymFormer demonstrates competitive results with 54.1% mIoU on NYUv2 and 49.1% mIoU on SUNRGBD. Notably, AsymFormer achieves an inference speed of 65 FPS (79 FPS after implementing mixed precision quantization) on RTX3090, demonstrating that AsymFormer can strike a balance between high accuracy and efficiency.