|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Most of the proposed person re-identification algorithms conduct supervised training and testing on single labeled datasets with small size, so directly deploying these trained models to a large-scale real-world camera network may lead to poor performance due to underfitting.
To overcome this problem, we propose a deep model for the soft multilabel learning for unsupervised RE-ID.
In order to mitigate the effects of noisy pseudo labels, we propose to softly refine the pseudo labels in the target domain by proposing an unsupervised framework, Mutual Mean-Teaching (MMT), to learn better features from the target domain via off-line refined hard pseudo labels and on-line refined soft pseudo labels in an alternative training manner.
Specifically, we develop a PatchNet to select patches from the feature map and learn discriminative features for these patches.
With this insight, we design a novel Dispersion-based Clustering (DBC) approach which can discover the underlying patterns in data.
In the first case, by treating each person image as an individual class, a non-parametric classifier with a feature memory is exploited to encourage person images to move away from each other.
In such a way, DECAMEL jointly learns the feature representation and the unsupervised asymmetric metric.
While metric learning is important for Person re-identification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires quantities of labeled samples in all pairs of camera views for training.
For training of deep re-ID model, we divide it into three steps: 1) pre-training a coarse re-ID model by using virtual data; 2) collaborative filtering based positive pair mining from the real data; and 3) fine-tuning of the coarse re-ID model by leveraging the mined positive pairs and virtual data.