|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
An effective person re-identification (re-ID) model should learn feature representations that are both discriminative, for distinguishing similar-looking people, and generalisable, for deployment across datasets without any adaptation.
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.
#38 best model for Person Re-Identification on DukeMTMC-reID
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.
SOTA for Unsupervised Person Re-Identification on DukeMTMC-reID->Market-1501 (mAP metric )
Upon our SSG, we further introduce a clustering-guided semisupervised approach named SSG ++ to conduct the one-shot domain adaption in an open set setting (i. e. the number of independent identities from the target domain is unknown).
Specifically, we develop a PatchNet to select patches from the feature map and learn discriminative features for these patches.
We evaluate our model on unsupervised person re-identification and pose-invariant face recognition.
With this insight, we design a novel Dispersion-based Clustering (DBC) approach which can discover the underlying patterns in data.
#3 best model for Unsupervised Person Re-Identification on Market-1501
However, a problem of the adaptive selection is that, when an image has too many neighborhoods, it is more likely to attract other images as its neighborhoods.
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.
#55 best model for Person Re-Identification on Market-1501