Thermal Image Segmentation On Rgb T Glass
Metriken
MAE
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | MAE |
|---|---|
| hierarchical-dynamic-filtering-network-for | 0.048 |
| rgb-d-salient-object-detection-with | 0.052 |
| shapeconv-shape-aware-convolutional-layer-for | 0.054 |
| select-supplement-and-focus-for-rgb-d | 0.097 |
| enhanced-boundary-learning-for-glass-like | 0.104 |
| glass-segmentation-with-rgb-thermal-image | 0.024 |
| uc-net-uncertainty-inspired-rgb-d-saliency | 0.071 |
| cmx-cross-modal-fusion-for-rgb-x-semantic | 0.029 |
| visual-saliency-transformer | 0.044 |
| segformer-simple-and-efficient-design-for | 0.053 |
| asymmetric-two-stream-architecture-for | 0.098 |
| learning-generative-vision-transformer-with-1 | 0.040 |
| specificity-preserving-rgb-d-saliency | 0.041 |
| depth-potentiality-aware-gated-attention | 0.154 |
| calibrated-rgb-d-salient-object-detection | 0.056 |
| efficient-rgb-d-semantic-segmentation-for | 0.040 |
| rgb-d-saliency-detection-via-cascaded-mutual | 0.041 |
| rtfnet-rgb-thermal-fusion-network-for | 0.058 |
| a-single-stream-network-for-robust-and-real | 0.069 |
| accurate-rgb-d-salient-object-detection-via | 0.145 |
| rgb-d-salient-object-detection-via-3d | 0.045 |
| segmenter-transformer-for-semantic | 0.072 |