Person Transfer GAN to Bridge Domain Gap for Person Re-identification

Wei, Longhui; Zhang, Shiliang; Gao, Wen; Tian, Qi

doi:10.1109/cvpr.2018.00016

Cited by 1,489 publications

(1,205 citation statements)

References 43 publications

Supporting

Mentioning

1,195

Contrasting

Order By: Relevance

“…To evaluate our proposed methods, we select three large publicly available person re-identification datasets namely Market-1501 [29], DukeMTMC-reID [30] and MSMT17 [31]. Market-1501 contains 32,668 images of 1,501 identities captured by 5 high-resolution cameras and one low-resolution camera.…”

Section: A Datasets and Protocolsmentioning

confidence: 99%

End-to-End Comparative Attention Networks for Person Re-Identification

Líu¹,

Feng²,

Qi³

et al. 2017

IEEE Trans. on Image Process.

547

317

View full text Add to dashboard Cite

Abstract-Person re-identification across disjoint camera views has been widely applied in video surveillance yet it is still a challenging problem. One of the major challenges lies in the lack of spatial and temporal cues, which makes it difficult to deal with large variations of lighting conditions, viewing angles, body poses and occlusions. Recently, several deep learning based person re-identification approaches have been proposed and achieved remarkable performance. However, most of those approaches extract discriminative features from the whole frame at one glimpse without differentiating various parts of the persons to identify. It is essentially important to examine multiple highly discriminative local regions of the person images in details through multiple glimpses for dealing with the large appearance variance.In this paper, we propose a new soft attention based model, i.e., the end-to-end Comparative Attention Network (CAN), specifically tailored for the task of person re-identification. The end-to-end CAN learns to selectively focus on parts of pairs of person images after taking a few glimpses of them and adaptively comparing their appearance. The CAN model is able to learn which parts of images are relevant for discerning persons and automatically integrates information from different parts to determine whether a pair of images belongs to the same person. In other words, our proposed CAN model simulates the human perception process to verify whether two images are from the same person. Extensive experiments on four benchmark person re-identification datasets, including CUHK01, CHUHK03, Market-1501 and VIPeR, clearly demonstrate that our proposed end-to-end CAN for person re-identification outperforms well established baselines significantly and offer new state-of-the-art performance.

show abstract

Section: A Datasets and Protocolsmentioning

confidence: 99%

End-to-End Comparative Attention Networks for Person Re-Identification

Líu¹,

Feng²,

Qi³

et al. 2017

IEEE Trans. on Image Process.

547

317

View full text Add to dashboard Cite

show abstract

“…Due to no existing re-id datasets for the proposed scenario, we introduced three ICS re-id benchmarks. We simulated the ICS identity annotation process on three existing large person re-id datasets, Market-1501 (Zheng et al, 2015), DukeMTMC-reID (Ristani et al, 2016;Zheng et al, 2017) and MSMT17 (Wei et al, 2018). Specifically, for the training data of each dataset, we independently perturbed the original identity labels for every individual camera view, and ensured that the same class labels of any pair of different camera views correspond to two unique persons (i.e.…”

Section: Methodsmentioning

confidence: 99%

“…Supervised person re-id Most existing person re-id models are created by supervised learning methods on a separate set of cross-camera identity labelled training data (Wang et al, 2014b(Wang et al, , 2016bZhao et al, 2017;Chen et al, 2017;Li et al, 2017;Chen et al, 2018b;Li et al, 2018b;Song et al, 2018;Chang et al, 2018;Sun et al, 2018;Shen et al, 2018a;Wei et al, 2018;Hou et al, 2019;Zheng et al, 2019;Zhang et al, 2019;Quan et al, 2019;Zhou et al, 2019). Relying on the strong supervision of cross-camera identity labelled training data, they have achieved remarkable performance boost.…”

Section: Related Workmentioning

confidence: 99%

Intra-Camera Supervised Person Re-Identification: A New Benchmark

Zhu

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

Existing person re-identification (re-id) methods mostly exploit a large set of cross-camera identity labelled training data. This requires a tedious data collection and annotation process, leading to poor scalability in practical re-id applications. On the other hand unsupervised re-id methods do not need identity label information, but they usually suffer from much inferior and insufficient model performance. To overcome these fundamental limitations, we propose a novel person reidentification paradigm based on an idea of independent per-camera identity annotation. This eliminates the most time-consuming and tedious inter-camera identity labelling process, significantly reducing the amount of human annotation efforts. Consequently, it gives rise to a more scalable and more feasible setting, which we call Intra-Camera Supervised (ICS) person re-id, for which we formulate a Multi-tAsk mulTi-labEl (MATE) deep learning method. Specifically, MATE is designed for self-discovering the cross-camera identity correspondence in a per-camera multi-task inference framework. Extensive experiments demonstrate the cost-effectiveness Camera 3 Camera 1 Camera 4 Camera 2 (a) (b) Fig. 1 (a) Person re-identification challenges. Each triplet bounded by a dashed box shows the images of a single person from different camera views. (b) Illustration of manually associating identities across camera-views. The dashed arrow denotes the comparison between two identities. The associated identities are bounded with red boxes.superiority of our method over the alternative approaches on three large person re-id datasets. For example, MATE yields 88.7% rank-1 score on Market-1501 in the proposed ICS person re-id setting, significantly outperforming unsupervised learning models and closely approaching conventional fully supervised learning competitors.

show abstract

“…Thanks to many public Re-ID datasets [1], [11], [40]- [44], great progress has been made for person Re-ID in recent years. In most existing Re-ID datasets, the resolution is low and the person images are usually blurred with indistinguishable characteristic detail, which imposes significant difficulty on the algorithm design.…”

Section: A Dataset Descriptionmentioning

confidence: 99%

Progressive Unsupervised Person Re-Identification by Tracklet Association With Spatio-Temporal Regularization

Xie

Zhou

et al. 2021

IEEE Trans. Multimedia

Self Cite

View full text Add to dashboard Cite

Existing methods for person re-identification (Re-ID) are mostly based on supervised learning which requires numerous manually labeled samples across all camera views for training. Such a paradigm suffers the scalability issue since in real-world Re-ID application, it is difficult to exhaustively label abundant identities over multiple disjoint camera views. To this end, we propose a progressive deep learning method for unsupervised person Re-ID in the wild by Tracklet Association with Spatio-Temporal Regularization (TASTR). In our approach, we first collect tracklet data within each camera by automatic person detection and tracking. Then, an initial Re-ID model is trained based on within-camera triplet construction for person representation learning. After that, based on the person visual feature and spatio-temporal constraint, we associate cross-camera tracklets to generate cross-camera triplets and update the Re-ID model. Lastly, with the refined Re-ID model, better visual feature of person can be extracted, which further promote the association of cross-camera tracklets. The last two steps are iterated multiple times to progressively upgrade the Re-ID model. To facilitate the study, we have collected a new 4K UHD video dataset named Campus-4K with full frames and full spatio-temporal information. Experimental results show that with the spatio-temporal constraint in the training phase, the proposed approach outperforms the state-of-the-art unsupervised methods by notable margins on DukeMTMC-reID, and achieves competitive performance to fully supervised methods on both DukeMTMC-reID and Campus-4K datasets.

show abstract

Person Transfer GAN to Bridge Domain Gap for Person Re-identification

Cited by 1,489 publications

References 43 publications

End-to-End Comparative Attention Networks for Person Re-Identification

End-to-End Comparative Attention Networks for Person Re-Identification

Intra-Camera Supervised Person Re-Identification: A New Benchmark

Progressive Unsupervised Person Re-Identification by Tracklet Association With Spatio-Temporal Regularization

Contact Info

Product

Resources

About