CUPR: Contrastive Unsupervised Learning for Person Re-identification
Most of the current person re-identification (Re-ID) algorithms require a large labeled training dataset to obtain better results. For example, domain adaptation-based approaches rely heavily on limited real-world data to alleviate the problem of domain shift. However, such assumptions are impractical and rarely hold, since the data is not freely accessible and requires expensive annotation. To address this problem, we propose a novel pure unsupervised learning approach using contrastive learning (CUPR). Our framework is a simple iterative approach that learns strong high-level features from raw pixels using contrastive learning and then performs clustering to generate pseudo-labels. We demonstrate that CUPR outperforms the unsupervised and semi-supervised state-of-the-art methods on Market-1501 and DukeMTMC-reID datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
ClusteringContrastive LearningDomain AdaptationPerson Re-IdentificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Depth-CUPRL: Depth-Imaged Contrastive Unsupervised Prioritized Representations in Reinforcement Learning for Mapless Navigation of Unmanned Aerial Vehicles
Reinforcement Learning (RL) has presented an impressive performance in video games through raw pixel imaging and continuous control tasks. However, RL performs poorly with high-dimensional observations such as raw pixel …
continuous-controlContinuous ControlContrastive LearningDecision Making+3CUPre: Cross-domain Unsupervised Pre-training for Few-Shot Cell Segmentation
While pre-training on object detection tasks, such as Common Objects in Contexts (COCO) [1], could significantly boost the performance of cell segmentation, it still consumes on massive fine-annotated cell images [2] wit…
Cell SegmentationContrastive LearningFew-shot Instance SegmentationInstance Segmentation+5Fully Unsupervised Person Re-identification viaSelective Contrastive Learning
Person re-identification (ReID) aims at searching the same identity person among images captured by various cameras. Unsupervised person ReID attracts a lot of attention recently, due to it works without intensive manual…
Contrastive LearningPerson Re-IdentificationRepresentation LearningUnsupervised Person Re-IdentificationCluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identification
Unsupervised person re-identification (Re-ID) aims to match pedestrian images from different camera views in unsupervised setting. Existing methods for unsupervised person Re-ID are usually built upon the pseudo labels f…
ClusteringContrastive LearningData AugmentationPerson Re-Identification+1Joint Generative and Contrastive Learning for Unsupervised Person Re-identification
Recent self-supervised contrastive learning provides an effective approach for unsupervised person re-identification (ReID) by learning invariance from different views (transformed versions) of an input. In this paper, w…
Contrastive LearningData AugmentationDomain AdaptationGenerative Adversarial Network+3