paper-with-me

홈 › Papers

Improved Instance Discrimination and Feature Compactness for End-to-End Person Search

2021-05-21 · IEEE Transactions on Circuits and Systems for Video Technology 2021 5 · Shaowei Hou, Cairong Zhao, Zhicheng Chen, Jun Wu, Zhihua Wei, Duoqian Miao

Person search aims to locate and retrieve specific pedestrians in scene images, including two subtasks, pedestrian detection and person re-identification. Recently, triplet loss has been widely used in person re-identification, which effectively improves the pedestrian features embedding and achieves superior performance. However, forming triplet in the person search is not an easy task. Most of the existing end-to-end person search methods are based on Faster R-CNN. The training process of person re-identification part is affected by the detector. It is difficult to form pedestrian triplets within a limited batch size. Also, there are many pedestrian identities in the person search dataset, but each pedestrian identity only has a few samples. It is difficult to learn a robust pedestrian feature representation for person search. To resolve the problem discussed above, a novel Feature Compactness (FC) Loss for the person search is designed, which efficiently improves the inter-class discrimination and intra-class compactness of pedestrian features embedding without the need for positive or negative pairs. Besides, we propose a pedestrian attention module (PAM) to help the network focuses more on pedestrian information and suppresses irrelevant background information. Our method achieves comparable performance on two benchmarks, CUHK-SYSU and PRW, and achieves 91.96% of mAP and 93.34% of rank1 accuracy on CUHK-SYSU.

📄 PDF Abstract BibTeX

Code (1)

Vill-Lab/2021-TCSVT-IIDFC pytorch

Tasks

Pedestrian DetectionPerson Re-IdentificationPerson SearchTriplet

Similar Papers 제목 키워드 기반

Strong but Simple Baseline with Dual-Granularity Triplet Loss for Visible-Thermal Person Re-Identification

2020-12-09 · Haijun Liu, Yanxia Chai, Xiaoheng Tan, Dong Li 외

In this letter, we propose a conceptually simple and effective dual-granularity triplet loss for visible-thermal person re-identification (VT-ReID). In general, ReID models are always trained with the sample-based triple…

Cross-Modal Person Re-IdentificationPerson Re-IdentificationTriplet

Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning

2022-03-27 · Liulei Li, Tianfei Zhou, Wenguan Wang, Lu Yang 외

Our target is to learn visual correspondence from unlabeled videos. We develop LIIR, a locality-aware inter-and intra-video reconstruction framework that fills in three missing pieces, i.e., instance discrimination, loca…

PositionRepresentation LearningVideo Reconstruction

Locality-Aware Inter- and Intra-Video Reconstruction for Self-Supervised Correspondence Learning

2022-01-01 · CVPR 2022 1 · Liulei Li, Tianfei Zhou, Wenguan Wang, Lu Yang 외

Our target is to learn visual correspondence from unlabeled videos. We develop LIIR, a locality-aware inter-and intra-video reconstruction framework that fills in three missing pieces, i.e., instance discrimination, …

PositionRepresentation LearningVideo Reconstruction

Discrepant and Multi-Instance Proxies for Unsupervised Person Re-Identification

2023-01-01 · ICCV 2023 1 · Chang Zou, Zeqi Chen, Zhichao Cui, Yuehu Liu 외

Most recent unsupervised person re-identification methods maintain a cluster uni-proxy for contrastive learning. However, due to the intra-class variance and inter-class similarity, the cluster uni-proxy is prone to …

Contrastive LearningPerson Re-IdentificationUnsupervised Person Re-Identification

DROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identification

2024-01-31 · Shuguang Dou, Xiangyang Jiang, Yuanpeng Tu, Junyao Gao 외

The paper introduces the Decouple Re-identificatiOn and human Parsing (DROP) method for occluded person re-identification (ReID). Unlike mainstream approaches using global features for simultaneous multi-task learning of…

Human ParsingMulti-Task LearningOccluded Person Re-IdentificationPerson Re-Identification