Unsupervised Person Re-identification by Deep Learning Tracklet Association

Mostexistingpersonre-identification(re-id)methods relyon supervised model learning on per-camera-pair manually labelled pairwise training data. This leads to poor scalability in practical re-id deployment due to the lack of exhaustive identity labelling of image positive and negative pairs for every camera pair... (read more)

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Person Re-Identification DukeTracklet TAUDL Rank-1 26.1 # 2
Rank-20 57.2 # 2
Rank-5 42.0 # 2
mAP 20.8 # 2
Person Re-Identification MSMT17 TAUDL Rank-1 28.4 # 13
mAP 12.5 # 14
Person Re-Identification PRID2011 TAUDL Rank-1 49.4 # 10
Rank-20 98.9 # 6
Rank-5 78.7 # 8

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet