Triplet Loss with Channel Attention for Person Re-identification

Daniel Organisciak, Chirine Riachy, Nauman Aslam, Hubert P. H. Shum

Research output: Contribution to journalConference articlepeer-review

5 Citations (Scopus)
64 Downloads (Pure)


The triplet loss function has seen extensive use within person re-identification. Most works focus on either improving the mining algorithm or adding new terms to the loss function itself. Our work instead concentrates on two other core components of the triplet loss that have been under-researched. First, we improve the standard Euclidean distance with dynamic weights, which are selected based on the standard deviation of features across the batch. Second, we exploit channel attention via a squeeze and excitation unit in the backbone model to emphasise important features throughout all layers of the model. This ensures that the output feature vector is a better representation of the image, and is also more suitable to use within our dynamically weighted Euclidean distance function. We demonstrate that our alterations provide significant performance improvement across popular reidentification data sets, including almost 10% mAP improvement on the CUHK03 data set. The proposed model attains results competitive with many state-of-the-art person re-identification models.
Original languageEnglish
Pages (from-to)161-169
Number of pages9
JournalJournal of WSCG
Issue number2
Publication statusPublished - 7 Oct 2019
Event27th International Conference on Computer Graphics, Visualization and Computer Vision 2019 - Primavera Hotel and Congress Center, Plzen, Czech Republic
Duration: 27 May 201931 May 2019


Dive into the research topics of 'Triplet Loss with Channel Attention for Person Re-identification'. Together they form a unique fingerprint.

Cite this