Deep Association Learning for Unsupervised Video Person Re-identification
This addresses the scalability and practicality issues in real-world video surveillance by eliminating the need for manual labeling, though it is an incremental improvement over existing unsupervised methods.
The paper tackles the problem of video person re-identification without using identity labels, proposing a Deep Association Learning scheme that jointly optimizes two margin-based association losses. It significantly outperforms state-of-the-art unsupervised methods on benchmarks like PRID 2011, iLIDS-VID, and MARS.
Deep learning methods have started to dominate the research progress of video-based person re-identification (re-id). However, existing methods mostly consider supervised learning, which requires exhaustive manual efforts for labelling cross-view pairwise data. Therefore, they severely lack scalability and practicality in real-world video surveillance applications. In this work, to address the video person re-id task, we formulate a novel Deep Association Learning (DAL) scheme, the first end-to-end deep learning method using none of the identity labels in model initialisation and training. DAL learns a deep re-id matching model by jointly optimising two margin-based association losses in an end-to-end manner, which effectively constrains the association of each frame to the best-matched intra-camera representation and cross-camera representation. Existing standard CNNs can be readily employed within our DAL scheme. Experiment results demonstrate that our proposed DAL significantly outperforms current state-of-the-art unsupervised video person re-id methods on three benchmarks: PRID 2011, iLIDS-VID and MARS.