Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification

Abstract

While metric learning is important for Person reidentification (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. However, this limits their scalabilities to realistic applications, in which a large amount of data over multiple disjoint camera views is available but not labelled. To overcome the problem, we propose unsupervised asymmetric metric learning for unsupervised RE-ID. Our model aims to learn an asymmetric metric, i.e., specific projection for each view, based on asymmetric clustering on cross-view person images. Our model finds a shared space where view-specific bias is alleviated and thus better matching performance can be achieved. Extensive experiments have been conducted on a baseline and five large-scale RE-ID datasets to demonstrate the effectiveness of the proposed model. Through the comparison, we show that our model works much more suitable for unsupervised RE-ID compared to classical unsupervised metric learning models. We also compare with existing unsupervised RE-ID methods, and our model outperforms them with notable margins. Specifically, we report the results on large-scale unlabelled RE-ID dataset, which is important but unfortunately less concerned in literatures. ClusteringCamera-1 Camera-2 Projected by U1

Learning to Adapt Invariance in Memory for Person Re-identification

“…These works mainly can be divided into two categories: 1) discovering pseudo labels for target dataset, and 2) reducing the source-target discrepancy in a common label space. For the first category, methods use a labeled source dataset to initialize a re-ID model and explore pseudo labels for target dataset based on clustering [10], [55], associating label with labeled source dataset [57], assigning label with nearest-neighbors [5], [22], [23], [54], or regarding camera style counterparts as positive sample [64]. These methods are closely related to our work in that using the relationship between target samples to refine the model.…”

Impostor Resilient Multimodal Metric Learning for Person Reidentification

“…In Table 2 three most recently proposed metrics CVAML [40], WARCA [36], and L-1 Graph [37] are compared with our IRM3 approach. All the three metrics have assumption of unimodal intercamera transform, rather than multimodal image space.…”

Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation

“…Market-1501. In Table 1, we compare our proposed model with the use of Bag-of-Words (BoW) [58] for matching (i.e., no transfer), four unsupervised re-ID approaches, including UMDL [42], PUL [15], CAMEL [54] and TAUDL [29], and seven cross-dataset re-ID methods, including PTGAN [51], SPGAN [12], TJ-AIDL [49], MMFA [35], HHL [61], CFSM [3] and ARN [32]. From this table, we see that our model achieved very promising [12] and HHL [61], we note that our model is able to generate cross-domain images conditioned on various poses rather than few camera styles.…”