Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting

ECCV 2018 Wei LiuShengcai LiaoWeidong HuXuezhi LiangXiao Chen

Though Faster R-CNN based two-stage detectors have witnessed significant boost in pedestrian detection accuracy, it is still slow for practical applications. One solution is to simplify this working flow as a single-stage detector... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
LEADERBOARD
Pedestrian Detection Caltech ALFNet + CityPersons dataset Reasonable Miss Rate 4.5 # 6
Pedestrian Detection Caltech ALFNet Reasonable Miss Rate 6.1 # 11
Pedestrian Detection CityPersons ALFNet Reasonable MR^-2 12.0 # 6
Heavy MR^-2 51.9 # 5
Partial MR^-2 11.4 # 5
Bare MR^-2 8.4 # 7
Small MR^-2 19.0 # 3
Medium MR^-2 5.7 # 3
Large MR^-2 6.6 # 3
Test Time 0.27 # 1