Paper Info
Title
Learning Sparse and Identity-preserved Hidden Attributes for Person Re-identification.
Abstract
Person re-identification (Re-ID) aims at matching person images captured in non-overlapping camera views. To represent person appearance, low-level visual features are sensitive to environmental changes, while high-level semantic attributes, such as “short-hair” or “long-hair”, are relatively stable. Hence, researches have started to design semantic attributes to reduce the visual ambiguity. However, to train a prediction model for semantic attributes, it requires plenty of annotations, which are hard to obtain in practical large-scale applications. To alleviate the reliance on annotation efforts, we propose to incrementally generate Deep Hidden Attribute (DHA) based on baseline deep network for newly uncovered annotations. In particular, we propose an auto-encoder model that can be plugged into any deep network to mine latent information in an unsupervised manner. To optimize the effectiveness of DHA, we reform the auto-encoder model with additional <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">orthogonal</italic> generation module, along with <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">identity-preserving</italic> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">sparsity</italic> constraints. 1) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Orthogonally generating</italic> : In order to make DHAs different from each other, Singular Vector Decomposition (SVD) is introduced to generate DHAs orthogonally. 2) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Identity-preserving constraint</italic> : The generated DHAs should be distinct for telling different persons, so we associate DHAs with person identities. 3) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sparsity constraint</italic> : To enhance the discriminability of DHAs, we also introduce the sparsity constraint to restrict the number of effective DHAs for each person. Experiments conducted on public datasets have validated the effectiveness of the proposed network. On two large-scale datasets, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</italic> , Market-1501 and DukeMTMC-reID, the proposed method outperforms the state-of-the-art methods.
Year
DOI
Venue
2020
10.1109/TIP.2019.2946975
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Keywords
DocType
Volume
Semantics,Deep learning,Visualization,Feature extraction,Image reconstruction,Clothing,Training
Journal
29
Issue
ISSN
Citations 
1
1057-7149
9
PageRank 
References 
Authors
0.52
23
6
Name
Order
Citations
PageRank
Zheng Wang135236.33
Junjun Jiang2113874.49
Yang Wu36015.12
Mang Ye430425.92
Xiang Bai53517149.87
Shin'ichi Satoh62093277.41