paper-with-me

Papers

Random Occlusion-recovery for Person Re-identification

2018-09-26 · Di Wu, Kun Zhang, Fei Cheng, Yang Zhao, Qi Liu, Chang-An Yuan, De-Shuang Huang

As a basic task of multi-camera surveillance system, person re-identification aims to re-identify a query pedestrian observed from non-overlapping multiple cameras or across different time with a single camera. Recently, deep learning-based person re-identification models have achieved great success in many benchmarks. However, these supervised models require a large amount of labeled image data, and the process of manual labeling spends much manpower and time. In this study, we introduce a method to automatically synthesize labeled person images and adopt them to increase the sample number per identity for person re-identification datasets. To be specific, we use block rectangles to randomly occlude pedestrian images. Then, a generative adversarial network (GAN) model is proposed to use paired occluded and original images to synthesize the de-occluded images that similar but not identical to the original image. Afterwards, we annotate the de-occluded images with the same labels of their corresponding raw images and use them to augment the number of samples per identity. Finally, we use the augmented datasets to train baseline model. The experiment results on CUHK03, Market-1501 and DukeMTMC-reID datasets show that the effectiveness of the proposed method.

📄 PDF Abstract BibTeX arXiv:1809.09970

Code (0)

등록된 구현이 없습니다.

Tasks

Generative Adversarial NetworkPerson Re-Identification

Similar Papers 제목 키워드 기반

Learning Feature Recovery Transformer for Occluded Person Re-identification

2023-01-05 · Boqiang Xu, Lingxiao He, Jian Liang, Zhenan Sun

One major issue that challenges person re-identification (Re-ID) is the ubiquitous occlusion over the captured persons. There are two main challenges for the occluded person Re-ID problem, i.e., the interference of noise…

Graph MatchingGraph SimilarityOccluded Person Re-IdentificationPerson Re-Identification

Hierarchical and Efficient Learning for Person Re-Identification

2020-05-18 · Jiangning Zhang, Liang Liu, Chao Xu, Yong liu

Recent works in the person re-identification task mainly focus on the model accuracy while ignore factors related to the efficiency, e.g. model size and latency, which are critical for practical application. In this pape…

Person Re-Identification

Exploring Stronger Transformer Representation Learning for Occluded Person Re-Identification

2024-10-21 · Zhangjian Ji, Donglin Cheng, Kai Feng

Due to some complex factors (e.g., occlusion, pose variation and diverse camera perspectives), extracting stronger feature representation in person re-identification remains a challenging task. In this paper, we proposed…

Contrastive LearningOccluded Person Re-IdentificationPerson Re-IdentificationRepresentation Learning

Erasing, Transforming, and Noising Defense Network for Occluded Person Re-Identification

2023-07-14 · Neng Dong, Liyan Zhang, Shuanglin Yan, Hao Tang 외

Occlusion perturbation presents a significant challenge in person re-identification (re-ID), and existing methods that rely on external visual cues require additional computational resources and only consider the issue o…

Adversarial DefenseOccluded Person Re-IdentificationPerson Re-Identification

Content-Adaptive Auto-Occlusion Network for Occluded Person Re-Identification

2023-07-05 · IEEE Transactions on Image Processing 2023 7 · Cairong Zhao, Zefan Qu, Xinyang Jiang, Yuanpeng Tu 외

The occluded person re-identification (ReID) aims to match person images captured in severely occluded environments. Current occluded ReID works mostly rely on auxiliary models or employ a part-to-part matching strategy.…

Occluded Person Re-IdentificationPerson Re-Identification