Set Augmented Triplet Loss for Video Person Re-Identification

Pengfei Fang, Pan Ji, Lars Petersson, Mehrtash Harandi; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021, pp. 464-473


Modern video person re-identification (re-ID) machines are often trained using a metric learning approach, supervised by a triplet loss. The triplet loss used in video re-ID is usually based on so-called clip features, each aggregated from a few frame features. In this paper, we propose to model the video clip as a set and instead study the distance between sets in the corresponding triplet loss. In contrast to the distance between clip representations, the distance between clip sets considers the pair-wise similarity of each element (i.e., frame representation) between two sets. This allows the network to directly optimize the feature representation at a frame level. Apart from the commonly-used set distance metrics (e.g., ordinary distance and Hausdorff distance), we further propose a hybrid distance metric, tailored for the set-aware triplet loss. Also, we propose a hard positive set construction strategy using the learned class prototypes in a batch. Our proposed method achieves state-of-the-art results across several standard benchmarks, demonstrating the advantages of the proposed method.

Related Material

[pdf] [arXiv]
@InProceedings{Fang_2021_WACV, author = {Fang, Pengfei and Ji, Pan and Petersson, Lars and Harandi, Mehrtash}, title = {Set Augmented Triplet Loss for Video Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2021}, pages = {464-473} }