Person Re-Identification by Camera Correlation Aware Feature Augmentation

By Ying-Cong Chen, Xiatian Zhu, Weishi Zheng, J. Lai. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017

334 citations recorded by the source corpus.

The challenge of person re-identification (re-id) is to match individual images of the same person captured by different non-overlapping camera views against significant and unknown cross-view feature distortion. While a large number of distance metric/subspace learning models have been developed for re-id, the cross-view transformations they learned are view-generic and thus potentially less effective in quantifying the feature distortion inherent to each camera view. Learning view-specific feature transformations for re-id (i.e., view-specific re-id), an under-studied approach, becomes an alternative resort for this problem. In this work, we formulate a novel view-specific person re-identification framework from the feature augmentation point of view, called Camera coR relation Aware Feature augmenTation (CRAFT). Specifically, CRAFT performs cross-view adaptation by automatically measuring camera correlation from cross-view visual data distribution and adaptively conducting feature augmentation to transform the original features into a new adaptive space. Through our augmentation framework, view-generic learning algorithms can be readily generalized to learn and optimize view-specific sub-models whilst simultaneously modelling view-generic discrimination information. Therefore, our framework not only inherits the strength of view-generic model learning but also provides an effective way to take into account view specific characteristics. Our CRAFT framework can be extended to jointly learn view-specific feature transformations for person re-id across a large network with more than two cameras, a largely under-investigated but realistic re-id setting. Additionally, we present a domain-generic deep person appearance representation which is designed particularly to be towards view invariant for facilitating cross-view adaptation by CRAFT. We conducted extensively comparative experiments to validate the superiority and advantages of our proposed framework over state-of-the-art competitors on contemporary challenging person re-id datasets.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/14108d0d3506be804f870f1fb102255a4e8f5faf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Shaogang Gong
2. Mang Ye
3. Xiatian Zhu
4. Pong Chi Yuen
5. Xiangyuan Lan
6. J. Lai
7. Jingya Wang
8. Weishi Zheng

In Computer Vision and Pattern Recognition

1. Mang Ye
2. Yi Yang
3. Shaogang Gong
4. Tao A. Xiang
5. Liang Zheng
6. Xiatian Zhu
7. Pong Chi Yuen
8. Xiangyuan Lan

Citations in the corpus

• Harmonious Attention Network for Person Re-identification (2018, background): “Most existing person re-id methods focus on supervised learning of identity-discriminative information, including ranking by pairwise constraints [23, 38], discriminative distance metric learning [13, 45, 40, 20, 41, 4], and deep learning [24, 18, 3, 39, 35, 19].”
• Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification (2018, methodology): “Most existing re-id studies follow the supervised learning paradigm such as optimising pairwise matching distance metrics [20, 52, 57, 49, 54, 47, 50, 5] or deep learning methods [27, 45, 51, 44, 4, 28].”
• Cross-Domain Adversarial Feature Learning for Sketch Re-identification (2018, methodology): “Existed person Re-ID methods [1, 3, 9, 33, 36] mostly focus on the distinguishable identity feature learning of different persons.”
• RGB-Infrared Cross-Modality Person Re-identification (2017, methodology): “Handcrafted features included HOG [4], LOMO [23] and HIPHOP [3].”
• Bi-Directional Center-Constrained Top-Ranking for Visible Thermal Person Re-Identification (2020, background): “[11] proposed a deep zero-padding network [44] for modality sharable feature representations learning.”
• Person Re-identification by Deep Learning Multi-scale Representations (2017, background): “Existing works focus on designing identity discriminative feature representation [17, 13, 74, 29, 38, 36] or learning matching distance metrics [22, 68, 77, 64, 40, 72, 62, 63, 65, 8] or their combination in a deep learning framework [25, 3, 60, 67, 51, 66].”
• Person Re-Identification by Deep Joint Learning of Multi-Loss Classification (2017, methodology): “…, 2013; Wang et al. , 2014b; Paisitkri-angkrai et al. , 2015; Zhang et al. , 2016; Wang et al. , 2016b; Wang et al. , 2016c; Wang et al. , 2016d; Chen et al. , 2017b] or their combination in deep learning framework [ Li et al. , 2014; Ahmed et al. , 2015; Wang et al. , 2016a; Xiao et al. ,…”
• Attribute-Aware Attention Model for Fine-grained Representation Learning (2018, neutral): “CRAFT-MFA+LOMO [6] 71.”