| RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion | | 62.7 | | RoadFormer+ (ConvNeXt-L) | 2024-07-31 |
| HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion | ✓ Link | 61.5 | | HAPNet | 2024-04-04 |
| Complementary Random Masking for RGB-Thermal Semantic Segmentation | ✓ Link | 61.4 | | CRM_RGBT_Seg | 2023-03-30 |
| Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation | ✓ Link | 61.3 | | Sigma-base | 2024-04-05 |
| CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving Scenes | ✓ Link | 59.98 | 72.7 (3090) | CSFNet-2 | 2024-07-01 |
| Delivering Arbitrary-Modal Semantic Segmentation | ✓ Link | 59.9 | | CMNeXt (B4) | 2023-03-02 |
| CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers | ✓ Link | 59.7 | | CMX (B4) | 2022-03-09 |
| Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning | ✓ Link | 59.3 | | DPLNet | 2023-12-01 |
| UniRGB-IR: A Unified Framework for RGB-Infrared Semantic Tasks via Adapter Tuning | ✓ Link | 59.3 | | UniRGB-IR | 2024-04-26 |
| Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance | ✓ Link | 59.2 | | SHIFNet | 2025-03-04 |
| IGFNet: Illumination-Guided Fusion Network for Semantic Scene Understanding using RGB-Thermal Images | ✓ Link | 59.0 | | IGFNet(B2) | 2023-12-04 |
| Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks | ✓ Link | 58.9 | | EAEFNet (ResNet-152) | 2023-03-28 |
| Context-Aware Interaction Network for RGB-T Semantic Segmentation | ✓ Link | 58.6% | | CAINet (MobileNet-V2) | 2024-01-03 |
| SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation | ✓ Link | 58.4 | | SpiderMesh (B4) | 2023-03-15 |
| CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers | ✓ Link | 58.2 | | CMX (B2) | 2022-03-09 |
| StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation | ✓ Link | 58.13 | | StitchFusion | 2024-08-02 |
| SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation | ✓ Link | 57.9 | | SpiderMesh (ResNet-152) | 2023-03-15 |
| CACFNet: Cross-Modal Attention Cascaded Fusion Network for RGB-T Urban Scene Parsing | | 57.8 | | CACFNet | 2023-09-14 |
| Variational Probabilistic Fusion Network for RGB-T Semantic Segmentation | | 57.61 | | VPFNet | 2023-07-17 |
| EGFNet: Edge-Aware Guidance Fusion Network for RGB–Thermal Urban Scene Parsing | ✓ Link | 57.5 | | EGFNet(ConvNeXt) | 2023-08-15 |
| DooDLeNet: Double DeepLab Enhanced Feature Fusion for Thermal-color Semantic Segmentation | | 57.3 | | DooDLeNet | 2022-04-21 |
| PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation | ✓ Link | 56.5 | | PAIF | 2023-08-08 |
| Residual Spatial Fusion Network for RGB-Thermal Semantic Segmentation | | 56.2 | | RSFNet (ResNet-101) | 2023-06-17 |
| GEBNet: Graph-Enhancement Branch Network for RGB-T Scene Parsing | | 56.2 | | GEBNet | 2022-10-31 |
| Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation | ✓ Link | 56.1 | | SegMiF | 2023-08-04 |
| SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation | ✓ Link | 56.1 | | SpiderMesh (ResNet-101) | 2023-03-15 |
| MTANet: Multitask-Aware Network With Hierarchical Multimodal Fusion for RGB-T Urban Scene Understanding | | 56.1 | | MTANet | 2022-04-05 |
| CEKD: Cross-Modal Edge-Privileged Knowledge Distillation for Semantic Scene Understanding Using Only Thermal Images | ✓ Link | 56.1 | | CENet | 2023-02-22 |
| CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving Scenes | ✓ Link | 56.05 | 106.3 (3090) | CSFNet-1 | 2024-07-01 |
| Channel and Spatial Relation-Propagation Network for RGB-Thermal Semantic Segmentation | | 56.0 | | CSRPNet | 2023-08-24 |
| Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks | ✓ Link | 55.9 | | EAFFNet (ResNet-50) | 2023-03-28 |
| FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation | ✓ Link | 55.3 | | FEANet | 2021-10-18 |
| RGB-T Semantic Segmentation with Location, Activation, and Sharpening | ✓ Link | 54.9 | | LASNet | 2022-10-26 |
| ABMDRNet: Adaptive-Weighted Bi-Directional Modality Difference Reduction Network for RGB-T Semantic Segmentation | | 54.8 | | ABMDRNet | 2021-06-19 |
| Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing | ✓ Link | 54.8 | | EGFNet | 2021-12-09 |
| SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers | ✓ Link | 54.8 | | SegFormer (B4) | 2021-05-31 |
| SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation | ✓ Link | 54.4 | | SpiderMesh (ResNet-50) | 2023-03-15 |
| SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers | ✓ Link | 53.2 | | SegFormer (B2) | 2021-05-31 |
| RTFNet: RGB-Thermal Fusion Network for Semantic Segmentation of Urban Scenes | ✓ Link | 53.2 | | RTFNet | 2019-03-13 |
| Deep High-Resolution Representation Learning for Visual Recognition | ✓ Link | 51.7 | | HRNet | 2019-08-20 |
| Adaptive Pyramid Context Network for Semantic Segmentation | ✓ Link | 49.0 | | APCNet | 2019-06-01 |
| Swin Transformer: Hierarchical Vision Transformer using Shifted Windows | ✓ Link | 49.0 | | SwinT | 2021-03-25 |
| PST900: RGB-Thermal Calibration, Dataset and Segmentation Network | ✓ Link | 48.4 | | PST900 | 2019-09-20 |
| FTNet: Feature Transverse Network for Thermal Image Semantic Segmentation | ✓ Link | 47.12 | | FTNet | 2021-10-26 |
| ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation | ✓ Link | 46.3 | | ACNet | 2019-05-24 |
| Depth-aware CNN for RGB-D Segmentation | ✓ Link | 46.1 | | Depth-aware CNN | 2018-03-19 |
| Pyramid Scene Parsing Network | ✓ Link | 46.1 | | PSPNet | 2016-12-04 |
| Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation | ✓ Link | 45.8 | | SA-Gate | 2020-07-17 |
| U-Net: Convolutional Networks for Biomedical Image Segmentation | ✓ Link | 45.1 | | UNet | 2015-05-18 |
| Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes | ✓ Link | 44.2 | | FRRN | 2016-11-24 |
| CCNet: Criss-Cross Attention for Semantic Segmentation | ✓ Link | 43.3 | | CCNet | 2018-11-28 |
| SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation | ✓ Link | 42.3 | | SegNet | 2015-11-02 |
| Dual Attention Network for Scene Segmentation | ✓ Link | 41.3 | | DANet | 2018-09-09 |
| MFNet: Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes | | 39.7 | | MFNet | 2017-12-14 |
| ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation | ✓ Link | 36.1 | | ERFNet | 2017-10-09 |