Back to Search
Start Over
Part-Relation-Aware Feature Fusion Network for Person Re-Identification
- Source :
- IEEE Signal Processing Letters. 28:743-747
- Publication Year :
- 2021
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2021.
-
Abstract
- The research of part-based methods has been proven as an effective way in person re-identification (Re-ID) task. However, in existing part-based Re-ID methods, the informative interactions and potential associations among parts are neglected, which demands further study. To fill this gap, we propose a novel Part-relation-aware Feature Fusion Network (PFFN) which achieves a part-level feature fusion and enhances the discrimination of part features by fully employing helpful information from associations among parts. More specifically, a Dual-stage Attention (DA) module, consisting of spatial and part-based channel attention, is proposed to exploit complementary benefits of two kinds of attention information, thereby facilitating model with learning more discriminative features. Furthermore, Part-relation Exploitation (PE) module is proposed to learn relation-aware part features where correlative information among parts are fully employed, thereby bringing a noticeable improvement in performance. Extensive experiments are conducted on four mainstream Re-ID datasets to verify the superiority of PFFN. Compared with baseline model, PFFN has gained rank-1 accuracy improvement of 18.2% on MSMT17-v2, 12.1% on the CUHK03-Labeled, 5.6% on DukeMTMC-reid and 1.3% on Market1501, compellingly validating its effectiveness.
- Subjects :
- Correlative
Feature fusion
Relation (database)
Exploit
business.industry
Computer science
Applied Mathematics
Feature extraction
020206 networking & telecommunications
02 engineering and technology
Machine learning
computer.software_genre
Task (project management)
Discriminative model
Signal Processing
0202 electrical engineering, electronic engineering, information engineering
Artificial intelligence
Electrical and Electronic Engineering
business
computer
Communication channel
Subjects
Details
- ISSN :
- 15582361 and 10709908
- Volume :
- 28
- Database :
- OpenAIRE
- Journal :
- IEEE Signal Processing Letters
- Accession number :
- edsair.doi...........cce38ab37626c706f7ac00f9d402f9ed