Domain Adaptive Person Search

Li, Junjie; Yan, Yichao; Wang, Guanshuo; Yu, Fufu; Jia, Qiong; Ding, Shouhong

doi:10.1007/978-3-031-19781-9_18

Cited by 12 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to its wide application prospects, person search has made rapid progress in recent years. Some works (Wang et al 2020;Yao and Xu 2020;Dong et al 2020b;Han et al 2019;Chen et al 2020b;Lan, Zhu, and Gong 2018a) optimize the pedestrian detection and re-ID tasks in person search separately (two-stage methods), while others (Xiao et al 2017;Li et al 2022;Cao et al 2022;Yan et al 2022;Yu et al 2022;Kim et al 2021;Li and Miao 2021;Han, Ko, and Sim 2021;Yan et al 2021Yan et al , 2023 regard two sub-tasks as a whole and jointly optimize them in an end-to-end manner (one-stage methods). Generally, existing person search methods can be roughly divided into two groups: fully supervised and weakly supervised methods.…”

Section: Person Searchmentioning

confidence: 99%

“…Most existing person search methods (Xiao et al 2017;Li et al 2022;Yan et al 2022;Kim et al 2021;Li and Miao 2021;Han, Ko, and Sim 2021;Yan et al 2021Yan et al , 2023Tian et al 2022) use ImageNet pre-trained models (Deng et al 2009), such as ResNet50 (He et al 2016), as the initialization model for feature extraction. However, ImageNet pre-training, which learns classification-related knowledge, is limited in its applicability to downstream tasks, particularly when the target task is significantly different (He, Girshick, and Dollar 2019).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Divide and Conquer: Hybrid Pre-training for Person Search

Tian,

Chen,

Liu

et al. 2024

AAAI

View full text Add to dashboard Cite

Large-scale pre-training has proven to be an effective method for improving performance across different tasks. Current person search methods use ImageNet pre-trained models for feature extraction, yet it is not an optimal solution due to the gap between the pre-training task and person search task (as a downstream task). Therefore, in this paper, we focus on pre-training for person search, which involves detecting and re-identifying individuals simultaneously. Although labeled data for person search is scarce, datasets for two sub-tasks person detection and re-identification are relatively abundant. To this end, we propose a hybrid pre-training framework specifically designed for person search using sub-task data only. It consists of a hybrid learning paradigm that handles data with different kinds of supervisions, and an intra-task alignment module that alleviates domain discrepancy under limited resources. To the best of our knowledge, this is the first work that investigates how to support full-task pre-training using sub-task data. Extensive experiments demonstrate that our pre-trained model can achieve significant improvements across diverse protocols, such as person search method, fine-tuning data, pre-training data and model backbone. For example, our model improves ResNet50 based NAE by 10.3% relative improvement w.r.t. mAP. Our code and pre-trained models are released for plug-and-play usage to the person search community (https://github.com/personsearch/PretrainPS).

show abstract

Section: Person Searchmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Divide and Conquer: Hybrid Pre-training for Person Search

Tian,

Chen,

Liu

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Some methods utilize cross-domain transfer learning [36], [37]. DAPS [38] presents a unsupervised domain adaptive person search paradigm.…”

Section: B Unsupervised Person Re-idmentioning

confidence: 99%

Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Search

Wang¹,

Pang²,

Cao³

et al. 2023

Preprint

View full text Add to dashboard Cite

Weakly supervised person search aims to perform joint pedestrian detection and re-identification (re-id) with only person bounding-box annotations. Recently, the idea of contrastive learning is initially applied to weakly supervised person search, where two common contrast strategies are memorybased contrast and intra-image contrast. We argue that current intra-image contrast is shallow, which suffers from spatiallevel and occlusion-level variance. In this paper, we present a novel deep intra-image contrastive learning using a Siamese network. Two key modules are spatial-invariant contrast (SIC) and occlusion-invariant contrast (OIC). SIC performs many-toone contrasts between two branches of Siamese network and dense prediction contrasts in one branch of Siamese network. With these many-to-one and dense contrasts, SIC tends to learn discriminative scale-invariant and location-invariant features to solve spatial-level variance. OIC enhances feature consistency with the masking strategy to learn occlusion-invariant features. Extensive experiments are performed on two person search datasets CUHK-SYSU and PRW, respectively. Our method achieves a state-of-the-art performance among weakly supervised one-step person search approaches. We hope that our simple intra-image contrastive learning can provide more paradigms on weakly supervised person search. The source code is available at https://github.com/jiabeiwangTJU/DICL.

show abstract