SVDNet for Pedestrian Retrieval

This paper proposes the SVDNet for retrieval problems, with focus on the application of person re-identification (re-ID). We view each weight vector within a fully connected (FC) layer in a convolutional neuron network (CNN) as a projection basis... (read more)

PDF Abstract ICCV 2017 PDF ICCV 2017 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Person Re-Identification CUHK03 detected SVDNet-ResNet50 MAP 37.3 # 10
Rank-1 41.5 # 10
Person Re-Identification CUHK03 detected SVDNet-CaffeNet MAP 24.9 # 12
Rank-1 27.7 # 12
Person Re-Identification DukeMTMC-reID SVDNet Rank-1 76.7 # 32
MAP 56.8 # 37
Person Re-Identification Market-1501 SVDNet Rank-1 82.3 # 44
MAP 62.1 # 55

Methods used in the Paper