Skip to main content
Search
Get published
Explore Journals
Books
About
My account
Search all SpringerOpen articles
Search
EURASIP Journal on Image and Video Processing
About
Articles
Submission Guidelines
Table 9 Comparison of network accuracy (mAP and rank-1) and complexity (M: Parameters and T: GFLOPS) with different pruning criteria of the PSFP approach on all the person ReID datasets. BFE, backbone feature extractor
From:
Exploiting prunability for person re-identification
Market-1501
DukeMTMC-reID
Methods
Criteria
mAP
rank-1
T
M
mAP
rank-1
T
M
PSFP+PCB(BFE)
l
1
-norm
68.7
90.0
2.6
12.0
60.6
78.8
2.6
12.0
PSFP+PCB(BFE)
l
2
-norm
69.4
90.4
2.6
12.0
60.7
78.5
2.6
12.0
Back to article page