paper-with-me

홈 › Papers

Towards Fewer Labels: Support Pair Active Learning for Person Re-identification

2022-04-21 · Dapeng Jin, Minxian Li

Supervised-learning based person re-identification (re-id) require a large amount of manual labeled data, which is not applicable in practical re-id deployment. In this work, we propose a Support Pair Active Learning (SPAL) framework to lower the manual labeling cost for large-scale person reidentification. The support pairs can provide the most informative relationships and support the discriminative feature learning. Specifically, we firstly design a dual uncertainty selection strategy to iteratively discover support pairs and require human annotations. Afterwards, we introduce a constrained clustering algorithm to propagate the relationships of labeled support pairs to other unlabeled samples. Moreover, a hybrid learning strategy consisting of an unsupervised contrastive loss and a supervised support pair loss is proposed to learn the discriminative re-id feature representation. The proposed overall framework can effectively lower the labeling cost by mining and leveraging the critical support pairs. Extensive experiments demonstrate the superiority of the proposed method over state-of-the-art active learning methods on large-scale person re-id benchmarks.

📄 PDF Abstract BibTeX arXiv:2204.10008

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningConstrained ClusteringPerson Re-Identification

Similar Papers 제목 키워드 기반

Active Reinforcement Learning for Personalized Stress Monitoring in Everyday Settings

2023-04-28 · Ali Tazarv, Sina Labbaf, Amir Rahmani, Nikil Dutt 외

Most existing sensor-based monitoring frameworks presume that a large available labeled dataset is processed to train accurate detection models. However, in settings where personalization is necessary at deployment time …

Active Learningreinforcement-learningReinforcement Learning

Deep Active Learning for Video-based Person Re-identification

2018-12-14 · Menglin Wang, Baisheng Lai, Zhongming Jin, Xiaojin Gong 외

It is prohibitively expensive to annotate a large-scale video-based person re-identification (re-ID) dataset, which makes fully supervised methods inapplicable to real-world deployment. How to maximally reduce the annota…

Active LearningPerson Re-IdentificationVideo-Based Person Re-Identification

One-Bit Active Query With Contrastive Pairs

2022-01-01 · CVPR 2022 1 · Yuhang Zhang, Xiaopeng Zhang, Lingxi Xie, Jie Li 외

How to achieve better results with fewer labeling costs remains a challenging task. In this paper, we present a new active learning framework, which for the first time incorporates contrastive learning into recently …

Active LearningContrastive Learning

How to Purchase Labels? A Cost-Effective Approach Using Active Learning Markets

2025-11-25 · Xiwen Huang, Pierre Pinson arxiv

We introduce and analyse active learning markets as a way to purchase labels, in situations where analysts aim to acquire additional data to improve model fitting, or to better train models for predictive analytics appli…

Active Learning

Near-Polynomially Competitive Active Logistic Regression

2025-03-07 · Yihan Zhou, Eric Price, Trung Nguyen

We address the problem of active logistic regression in the realizable setting. It is well known that active learning can require exponentially fewer label queries compared to passive learning, in some cases using $\log …

Active Learningregression