Semantic Segmentation on FMB
0.741mIoURoadFormer+ (L)
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| RoadFormer+ (L)Model Scale=Large, Rank=12024.07 | 0.741 | — | — | — | — | — | — | — | |
| RoadFormer+ (B)Model Scale=Base2024.07 | 0.731 | — | — | — | — | — | — | — | |
| RoadFormer (B)Model Scale=Base, Rank=22024.07 | 0.692 | — | — | — | — | — | — | — | |
| SHIFNetModalities=RGB-Thermal2025.03 | 0.678 | — | — | — | — | — | — | — | |
| TUNI-BBackbone=TUNI-B, Params(M)=29.57, FLOPs(G)=42.64, FPS (RTX 4090)=60, FPS (Jetson Orin NX - CUDA)=6, FPS (Jetson Orin NX - TensorRT BF16)=14, Image Resolution=640 x 4802025.09 | 0.663 | — | — | — | — | — | — | — | |
| MCNet-TBackbone=ConvNextV2-B, Params(M)=199.79, FLOPs(G)=278.85, FPS (RTX 4090)=32, Image Resolution=640 x 4802025.09 | 0.636 | — | — | — | — | — | — | — | |
| TUNI-SBackbone=TUNI-S, Params(M)=10.63, FLOPs(G)=17.16, FPS (RTX 4090)=120, FPS (Jetson Orin NX - CUDA)=11, FPS (Jetson Orin NX - TensorRT BF16)=27, Image Resolution=640 x 4802025.09 | 0.635 | — | — | — | — | — | — | — | |
| LRRNet2026.03 | 0.6294 | — | 0.8971 | 0.5908 | 0.8669 | 0.346 | 0.6697 | 0.9568 | |
| Ours2026.03 | 0.6294 | — | 0.8955 | 0.6592 | 0.8718 | 0.3635 | 0.6758 | 0.9597 | |
| TIMFusion2026.03 | 0.6284 | — | 0.8991 | 0.5666 | 0.8702 | 0.3295 | 0.6602 | 0.9587 | |
| TUNI†Backbone=TUNI-S, Params(M)=10.63, FLOPs(G)=17.16, FPS (RTX 4090)=120, FPS (Jetson Orin NX - CUDA)=11, FPS (Jetson Orin NX - TensorRT BF16)=27, Image Resolution=640 x 4802025.09 | 0.624 | — | — | — | — | — | — | — | |
| TUNI-TBackbone=TUNI-T, Params(M)=4.99, FLOPs(G)=10.82, FPS (RTX 4090)=135, FPS (Jetson Orin NX - CUDA)=16, FPS (Jetson Orin NX - TensorRT BF16)=35, Image Resolution=640 x 4802025.09 | 0.624 | — | — | — | — | — | — | — | |
| EMMA2026.03 | 0.6195 | — | 0.9013 | 0.5569 | 0.8758 | 0.3319 | 0.6832 | 0.9606 | |
| MiLNetBackbone=Mit-B3, Params(M)=92.29, FLOPs(G)=136.32, FPS (RTX 4090)=25, FPS (Jetson Orin NX - CUDA)=2, Image Resolution=640 x 4802025.09 | 0.618 | — | — | — | — | — | — | — | |
| SigmaBackbone=Vmamba-T, Params(M)=48.3, FLOPs(G)=89.5, FPS (RTX 4090)=19, Image Resolution=640 x 4802025.09 | 0.618 | — | — | — | — | — | — | — | |
| VIS2026.03 | 0.6179 | — | 0.8946 | 0.5872 | 0.8567 | 0.3392 | 0.6709 | 0.9598 | |
| MMSFormerModalities=RGB-Thermal2025.03 | 0.617 | — | — | — | — | — | — | — | |
| MMSFormerRank=32024.07 | 0.617 | — | — | — | — | — | — | — | |
| CDDFuse2026.03 | 0.6165 | — | 0.8981 | 0.579 | 0.8738 | 0.3299 | 0.6775 | 0.9606 | |
| DFormerV2Backbone=DFormerV2-S, Params(M)=26.70, FLOPs(G)=33.90, FPS (RTX 4090)=33, FPS (Jetson Orin NX - CUDA)=2, FPS (Jetson Orin NX - TensorRT BF16)=11, Image Resolution=640 x 4802025.09 | 0.615 | — | — | — | — | — | — | — | |
| DFormerBackbone=DFormer-B, Params(M)=29.5, FLOPs(G)=41.9, FPS (RTX 4090)=69, FPS (Jetson Orin NX - CUDA)=5, FPS (Jetson Orin NX - TensorRT BF16)=15, Image Resolution=640 x 4802025.09 | 0.612 | — | — | — | — | — | — | — | |
| CMXBackbone=Mit-B2, Params(M)=66.57, FLOPs(G)=67.20, FPS (RTX 4090)=63, FPS (Jetson Orin NX - CUDA)=3, FPS (Jetson Orin NX - TensorRT BF16)=13, Image Resolution=640 x 4802025.09 | 0.611 | — | — | — | — | — | — | — | |
| CPALBackbone=Swin-T, Params(M)=52.70, Image Resolution=640 x 4802025.09 | 0.609 | — | — | — | — | — | — | — | |
| TIMFTask Network Retraining=true, Downstream Task Network=SegFormer mit-b2, Input Resolution=600x800, Params (M)=46.52, FLOPs (G)=183.822026.04 | 0.6086 | — | — | — | — | — | — | — | |
| U2Fusion2026.03 | 0.6083 | — | 0.8952 | 0.5784 | 0.8523 | 0.3385 | 0.6508 | 0.9497 | |
| IVFWSR2026.03 | 0.608 | — | 0.8867 | 0.59 | 0.8571 | 0.3431 | 0.6328 | 0.9532 | |
| U3MModalities=RGB-Thermal2025.03 | 0.608 | — | — | — | — | — | — | — | |
| SAGE2026.03 | 0.6078 | — | 0.8819 | 0.5575 | 0.8668 | 0.3372 | 0.6607 | 0.9577 | |
| TDFusionBackbone=SegFormer, Training Epochs=3002024.12 | 0.605 | 0.6717 | — | — | — | — | — | — | |
| AGFNetBackbone=ResNet50, Params(M)=72.19, FLOPs(G)=219.11, Image Resolution=640 x 4802025.09 | 0.605 | — | — | — | — | — | — | — | |
| CLNet-TBackbone=Mit-B4, Params(M)=130.84, FLOPs(G)=217.85, FPS (RTX 4090)=28, FPS (Jetson Orin NX - CUDA)=1, Image Resolution=640 x 4802025.09 | 0.604 | — | — | — | — | — | — | — | |
| DCEvo2026.03 | 0.6037 | — | 0.8937 | 0.5656 | 0.8723 | 0.3388 | 0.6851 | 0.9608 | |
| CLDyNTask Network Retraining=true, Downstream Task Network=SegFormer mit-b2, Input Resolution=600x800, Params (M)=0.46, FLOPs (G)=174.062026.04 | 0.6034 | — | — | — | — | — | — | — | |
| TDFuTask Network Retraining=true, Downstream Task Network=SegFormer mit-b2, Input Resolution=600x800, Params (M)=46.52, FLOPs (G)=183.822026.04 | 0.6012 | — | — | — | — | — | — | — | |
| TDALTask Network Retraining=true, Downstream Task Network=SegFormer mit-b2, Input Resolution=600x800, Params (M)=46.52, FLOPs (G)=183.822026.04 | 0.598 | — | — | — | — | — | — | — | |
| IRFSTask Network Retraining=true, Downstream Task Network=SegFormer mit-b2, Input Resolution=600x800, Params (M)=46.52, FLOPs (G)=183.822026.04 | 0.5943 | — | — | — | — | — | — | — | |
| TextIFTask Network Retraining=true, Downstream Task Network=SegFormer mit-b2, Input Resolution=600x800, Params (M)=46.52, FLOPs (G)=183.822026.04 | 0.5936 | — | — | — | — | — | — | — | |
| SMiFTask Network Retraining=true, Downstream Task Network=SegFormer mit-b2, Input Resolution=600x800, Params (M)=46.52, FLOPs (G)=183.822026.04 | 0.5915 | — | — | — | — | — | — | — | |
| CMNextBackbone=Mit-B2, Params(M)=58.68, FLOPs(G)=68.70, FPS (RTX 4090)=67, FPS (Jetson Orin NX - CUDA)=3, FPS (Jetson Orin NX - TensorRT BF16)=11, Image Resolution=640 x 4802025.09 | 0.59 | — | — | — | — | — | — | — | |
| CM-SSMBackbone=EfficientVit-B1, Params(M)=10.34, FLOPs(G)=12.59, FPS (RTX 4090)=114, FPS (Jetson Orin NX - CUDA)=9, FPS (Jetson Orin NX - TensorRT BF16)=42, Image Resolution=640 x 4802025.09 | 0.59 | — | — | — | — | — | — | — | |
| CoCoTask Network Retraining=true, Downstream Task Network=SegFormer mit-b2, Input Resolution=600x800, Params (M)=46.52, FLOPs (G)=183.822026.04 | 0.5895 | — | — | — | — | — | — | — | |
| OCCOTask Network Retraining=true, Downstream Task Network=SegFormer mit-b2, Input Resolution=600x800, Params (M)=46.52, FLOPs (G)=183.822026.04 | 0.5857 | — | — | — | — | — | — | — | |
| CoCoNet2026.03 | 0.5851 | — | 0.8963 | 0.578 | 0.866 | 0.3249 | 0.6498 | 0.9565 | |
| SegMIFBackbone=SegFormer, Training Epochs=3002024.12 | 0.5841 | 0.6597 | — | — | — | — | — | — | |
| MRFSTask Network Retraining=true, Downstream Task Network=SegFormer mit-b2, Input Resolution=600x800, Params (M)=46.52, FLOPs (G)=183.822026.04 | 0.5828 | — | — | — | — | — | — | — | |
| VisibleBackbone=SegFormer, Training Epochs=3002024.12 | 0.5796 | 0.6512 | — | — | — | — | — | — | |
| TIMFusionBackbone=SegFormer, Training Epochs=3002024.12 | 0.5724 | 0.637 | — | — | — | — | — | — | |
| MURFBackbone=SegFormer, Training Epochs=3002024.12 | 0.5696 | 0.641 | — | — | — | — | — | — | |
| EMMABackbone=SegFormer, Training Epochs=3002024.12 | 0.5628 | 0.6245 | — | — | — | — | — | — | |
| TarDAL2026.03 | 0.5619 | — | 0.8746 | 0.527 | 0.7701 | 0.314 | 0.5312 | 0.9076 | |
| SGFNetBackbone=ResNet50, Params(M)=125.25, FLOPs(G)=144.83, FPS (RTX 4090)=42, FPS (Jetson Orin NX - CUDA)=2, Image Resolution=640 x 4802025.09 | 0.56 | — | — | — | — | — | — | — | |
| MRFSBackbone=SegFormer, Training Epochs=3002024.12 | 0.5571 | 0.6193 | — | — | — | — | — | — | |
| TarDALBackbone=SegFormer, Training Epochs=3002024.12 | 0.5533 | 0.6286 | — | — | — | — | — | — | |
| SAGETask Network Retraining=true, Downstream Task Network=SegFormer mit-b2, Input Resolution=600x800, Params (M)=46.52, FLOPs (G)=183.822026.04 | 0.5489 | — | — | — | — | — | — | — | |
| DCINNBackbone=SegFormer, Training Epochs=3002024.12 | 0.5481 | 0.6109 | — | — | — | — | — | — | |
| SegMiFModalities=RGB-Thermal2025.03 | 0.548 | — | — | — | — | — | — | — | |
| SegMiFRank=42024.07 | 0.548 | — | — | — | — | — | — | — | |
| InfraredBackbone=SegFormer, Training Epochs=3002024.12 | 0.5198 | 0.5885 | — | — | — | — | — | — | |
| ReCoNetModalities=RGB-Thermal2025.03 | 0.509 | — | — | — | — | — | — | — | |
| ReCoNetRank=52024.07 | 0.509 | — | — | — | — | — | — | — | |
| DIDFuseModalities=RGB-Thermal2025.03 | 0.506 | — | — | — | — | — | — | — | |
| DIDFuseRank=62024.07 | 0.506 | — | — | — | — | — | — | — | |
| FGDNet-SBackbone=Res18+Mit-B0, Params(M)=17.96, FLOPs(G)=38.71, Image Resolution=640 x 4802025.09 | 0.497 | — | — | — | — | — | — | — | |
| CMNetModalities=RGB-Thermal2025.03 | 0.492 | — | — | — | — | — | — | — | |
| GMNetBackbone=ResNet101, Params(M)=191.24, FLOPs(G)=195.37, FPS (RTX 4090)=41, FPS (Jetson Orin NX - CUDA)=4, Image Resolution=640 x 4802025.09 | 0.492 | — | — | — | — | — | — | — | |
| U2FusionModalities=RGB-Thermal2025.03 | 0.479 | — | — | — | — | — | — | — | |
| LASNetModalities=RGB-Thermal2025.03 | 0.425 | — | — | — | — | — | — | — |