Lane Detection On Culane
Métriques
F1 score
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | F1 score |
|---|---|
| spatial-as-deep-spatial-cnn-for-traffic-scene | 71.6 |
| end-to-end-lane-detection-with-one-to-several | 78.0 |
| clrernet-improving-confidence-of-lane | 81.12 |
| lane-detection-with-versatile-atrousformer | 77.63 |
| a-keypoint-based-global-association-network | 78.79 |
| canet-curved-guide-line-network-with-adaptive | 78.46 |
| clrnet-cross-layer-refinement-network-for | 80.47 |
| clrmatchnet-enhancing-curved-lane-detection | 80.00 |
| clrnet-cross-layer-refinement-network-for | 79.58 |
| eigenlanes-data-driven-lane-descriptors-for | 77.2 |
| clrernet-improving-confidence-of-lane | 80.91 |
| swiftlane-towards-fast-and-efficient-lane | 74.03 |
| keep-your-eyes-on-the-lane-attention-guided | 75.13 |
| curvelane-nas-unifying-lane-sensitive | 73.5 |
| contrastive-learning-for-lane-detection-via | 70.56 |
| clrnet-cross-layer-refinement-network-for | 80.13 |
| fenet-focusing-enhanced-network-for-lane | 80.15 |
| lane-detection-with-versatile-atrousformer | 78.08 |
| clrkdnet-speeding-up-lane-detection-with | 79.66 |
| learning-lightweight-lane-detection-cnns-by | 70.8 |
| ultra-fast-structure-aware-deep-lane | 72.3 |
| a-keypoint-based-global-association-network | 79.39 |
| a-keypoint-based-global-association-network | 79.63 |
| clrkdnet-speeding-up-lane-detection-with | 80.68 |
| clrernet-improving-confidence-of-lane | 80.76 |
| 190503704 | 68.8 |
| curvelane-nas-unifying-lane-sensitive | 74.8 |
| ultra-fast-structure-aware-deep-lane | 68.4 |
| structure-guided-lane-detection | 77.27 |
| generating-dynamic-kernels-via-transformers | 80.77 |
| canet-curved-guide-line-network-with-adaptive | 79.16 |
| laneaf-robust-multi-lane-detection-with | 74.24 |
| condlanenet-a-top-to-down-lane-detection | 79.48 |
| canet-curved-guide-line-network-with-adaptive | 79.86 |
| laneaf-robust-multi-lane-detection-with | 77.41 |
| condlanenet-a-top-to-down-lane-detection | 78.74 |
| keep-your-eyes-on-the-lane-attention-guided | 76.68 |
| keep-your-eyes-on-the-lane-attention-guided | 77.02 |
| curvelane-nas-unifying-lane-sensitive | 71.4 |
| laneaf-robust-multi-lane-detection-with | 75.63 |
| end-to-end-lane-marker-detection-via-row-wise | 74 |
| generating-dynamic-kernels-via-transformers | 80.36 |
| clrnet-cross-layer-refinement-network-for | 79.73 |
| contrastive-learning-for-lane-detection-via | 79.27 |
| key-points-estimation-and-point-instance | 74.4 |
| rethinking-efficient-lane-detection-via-curve | 75.57 |
| condlanenet-a-top-to-down-lane-detection | 78.14 |
| contrastive-learning-for-lane-detection-via | 76.26 |
| focus-on-local-detecting-lane-marker-from | 78.8 |
| eigenlanes-data-driven-lane-descriptors-for | 76.5 |
| resa-recurrent-feature-shift-aggregator-for | 75.3 |
| end-to-end-lane-marker-detection-via-row-wise | 71.9 |
| fenet-focusing-enhanced-network-for-lane | 80.19 |
| inter-region-affinity-distillation-for-road | 72.4 |
| generating-dynamic-kernels-via-transformers | 80.55 |
| robust-lane-detection-via-expanded-self | 74.2 |
| rethinking-efficient-lane-detection-via-curve | 73.67 |