Thermal Image Segmentation On Mfn Dataset
Metrics
mIOU
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | mIOU |
|---|---|
| full-resolution-residual-networks-for | 44.2 |
| unirgb-ir-a-unified-framework-for-visible | 59.3 |
| dual-attention-network-for-scene-segmentation | 41.3 |
| spidermesh-spatial-aware-demand-guided | 54.4 |
| ccnet-criss-cross-attention-for-semantic | 43.3 |
| egfnet-edge-aware-guidance-fusion-network-for | 57.5 |
| efficient-multimodal-semantic-segmentation | 59.3 |
| csfnet-a-cosine-similarity-fusion-network-for | 59.98 |
| cmx-cross-modal-fusion-for-rgb-x-semantic | 59.7 |
| segnet-a-deep-convolutional-encoder-decoder | 42.3 |
| feanet-feature-enhanced-attention-network-for | 55.3 |
| segformer-simple-and-efficient-design-for | 53.2 |
| sigma-siamese-mamba-network-for-multi-modal | 61.3 |
| rtfnet-rgb-thermal-fusion-network-for | 53.2 |
| segformer-simple-and-efficient-design-for | 54.8 |
| gebnet-graph-enhancement-branch-network-for | 56.2 |
| explicit-attention-enhanced-fusion-for-rgb | 58.9 |
| residual-spatial-fusion-network-for-rgb | 56.2 |
| channel-and-spatial-relation-propagation | 56.0 |
| doodlenet-double-deeplab-enhanced-feature | 57.3 |
| csfnet-a-cosine-similarity-fusion-network-for | 56.05 |
| mfnet-towards-real-time-semantic-segmentation | 39.7 |
| hapnet-toward-superior-rgb-thermal-scene | 61.5 |
| roadformer-delivering-rgb-x-scene-parsing | 62.7 |
| bi-directional-cross-modality-feature | 45.8 |
| cekd-cross-modal-edge-privileged-knowledge | 56.1 |
| mtanet-multitask-aware-network-with | 56.1 |
| explicit-attention-enhanced-fusion-for-rgb | 55.9 |
| variational-probabilistic-fusion-network-for | 57.61 |
| 190807919 | 51.7 |
| swin-transformer-hierarchical-vision | 49.0 |
| unveiling-the-potential-of-segment-anything | 59.2 |
| pyramid-scene-parsing-network | 46.1 |
| context-aware-interaction-network-for-rgb-t | 58.6% |
| spidermesh-spatial-aware-demand-guided | 58.4 |
| ftnet-feature-transverse-network-for-thermal | 47.12 |
| igfnet-illumination-guided-fusion-network-for | 59.0 |
| delivering-arbitrary-modal-semantic | 59.9 |
| multi-interactive-feature-learning-and-a-full | 56.1 |
| erfnet-efficient-residual-factorized-convnet | 36.1 |
| pst900-rgb-thermal-calibration-dataset-and | 48.4 |
| cmx-cross-modal-fusion-for-rgb-x-semantic | 58.2 |
| 2408-01343 | 58.13 |
| spidermesh-spatial-aware-demand-guided | 57.9 |
| abmdrnet-adaptive-weighted-bi-directional | 54.8 |
| edge-aware-guidance-fusion-network-for-rgb | 54.8 |
| paif-perception-aware-infrared-visible-image | 56.5 |
| spidermesh-spatial-aware-demand-guided | 56.1 |
| u-net-convolutional-networks-for-biomedical | 45.1 |
| complementary-random-masking-for-rgb-thermal | 61.4 |
| cacfnet-cross-modal-attention-cascaded-fusion | 57.8 |
| acnet-attention-based-network-to-exploit | 46.3 |
| depth-aware-cnn-for-rgb-d-segmentation | 46.1 |
| rgb-t-semantic-segmentation-with-location | 54.9 |
| adaptive-pyramid-context-network-for-semantic | 49.0 |