Learning Discriminative Features with Multiple Granularities for Person Re-Identification

4 Apr 2018 Guanshuo Wang Yufeng Yuan Xiong Chen Jiwei Li Xi Zhou

The combination of global and partial features has been an essential solution to improve discriminative performances in person re-identification (Re-ID) tasks. Previous part-based methods mainly focus on locating regions with specific pre-defined semantics to learn local representations, which increases learning difficulty but not efficient or robust to scenarios with large variances... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Person Re-Identification CUHK03 detected MGN (ACM MM'18) MAP 66.0 # 7
Rank-1 68.0 # 7
Person Re-Identification CUHK03 labeled MGN (ACM MM'18) MAP 67.4 # 7
Rank-1 68.0 # 6
Person Re-Identification DukeMTMC-reID MGN Rank-1 88.7 # 16
MAP 78.4 # 24
Person Re-Identification Market-1501 MGN Rank-1 95.7 # 8
MAP 86.9 # 24

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