Pedestrian Detection On Caltech
Metrics
Reasonable Miss Rate
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Reasonable Miss Rate |
|---|---|
| crowdhuman-a-benchmark-for-detecting-human-in | 3.46 |
| occlusion-aware-r-cnn-detecting-pedestrians | 4.1 |
| learning-efficient-single-stage-pedestrian | 6.1 |
| f2dnet-fast-focal-detection-network-for | 1.71 |
| pedestrian-detection-inspired-by-appearance | 16.20 |
| a-unified-multi-scale-deep-convolutional | 9.95 |
| high-level-semantic-feature-detectiona-new | 3.8 |
| fused-dnn-a-deep-neural-network-fusion | 8.18 |
| citypersons-a-diverse-dataset-for-pedestrian | 5.1 |
| repulsion-loss-detecting-pedestrians-in-a | 4.0 |
| repulsion-loss-detecting-pedestrians-in-a | 5.0 |
| pedestrian-detection-aided-by-deep-learning | 20.9 |
| f2dnet-fast-focal-detection-network-for | 2.2 |
| local-decorrelation-for-improved-pedestrian | 24.8 |
| taking-a-deeper-look-at-pedestrians | 23.3 |
| is-faster-r-cnn-doing-well-for-pedestrian | 8.7 |
| citypersons-a-diverse-dataset-for-pedestrian | 5.8 |
| part-level-convolutional-neural-networks-for | 12.4 |
| is-faster-r-cnn-doing-well-for-pedestrian | 7.3 |
| nms-loss-learning-with-non-maximum | 2.92 |
| vlpd-context-aware-pedestrian-detection-via | 2.3 |
| unihcp-a-unified-model-for-human-centric | - |
| filtered-channel-features-for-pedestrian | 17.1 |
| learning-complexity-aware-cascades-for-deep | 11.75 |
| illuminating-pedestrians-via-simultaneous | 7.36 |
| temporal-context-enhanced-detection-of | 6.5 |
| high-level-semantic-feature-detectiona-new | 4.5 |
| pedestrian-detection-the-elephant-in-the-room | 1.76 |
| scale-aware-fast-r-cnn-for-pedestrian | 9.68 |
| what-can-help-pedestrian-detection | 5.5 |
| learning-efficient-single-stage-pedestrian | 4.5 |
| learning-multilayer-channel-features-for | 10.40 |
| localized-semantic-feature-mixers-for | 0.87 |