Improved Instance Discrimination and Feature Compactness for End-to-End Person Search
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.
Code (1)
Tasks
Pedestrian DetectionPerson Re-IdentificationPerson SearchTripletSimilar Papers 제목 키워드 기반
Strong but Simple Baseline with Dual-Granularity Triplet Loss for Visible-Thermal Person Re-Identification
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-IdentificationTripletLocality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning
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 ReconstructionLocality-Aware Inter- and Intra-Video Reconstruction for Self-Supervised Correspondence Learning
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 ReconstructionDiscrepant and Multi-Instance Proxies for Unsupervised Person Re-Identification
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-IdentificationDROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identification
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