BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation
Single-stage multi-person human pose estimation (MPPE) methods have shown great performance improvements, but existing methods fail to disentangle features by individual instances under crowded scenes. In this paper, we propose a bounding box-level instance representation learning called BoIR, which simultaneously solves instance detection, instance disentanglement, and instance-keypoint association problems. Our new instance embedding loss provides a learning signal on the entire area of the image with bounding box annotations, achieving globally consistent and disentangled instance representation. Our method exploits multi-task learning of bottom-up keypoint estimation, bounding box regression, and contrastive instance embedding learning, without additional computational cost during inference. BoIR is effective for crowded scenes, outperforming state-of-the-art on COCO val (0.8 AP), COCO test-dev (0.5 AP), CrowdPose (4.9 AP), and OCHuman (3.5 AP). Code will be available at https://github.com/uyoung-jeong/BoIR
Code (1)
Tasks
DisentanglementKeypoint EstimationMulti-Person Pose EstimationMulti-Task LearningPose EstimationRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ILPS at TREC 2017 Common Core Track
The TREC 2017 Common Core Track aimed at gathering a diverse set of participating runs and building a new test collection using advanced pooling methods. In this paper, we describe the participation of the IlpsUvA team…
Bayesian OptimizationRetrievalICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification
Unsupervised person re-identification (ReID) aims at learning discriminative identity features without annotations. Recently, self-supervised contrastive learning has gained increasing attention for its effectiveness in …
Contrastive LearningPerson Re-IdentificationRepresentation LearningUnsupervised Person Re-IdentificationLAMP: Leveraging Language Prompts for Multi-person Pose Estimation
Human-centric visual understanding is an important desideratum for effective human-robot interaction. In order to navigate crowded public places, social robots must be able to interpret the activity of the surrounding hu…
Language ModelingLanguage ModellingMulti-Person Pose EstimationNavigate+1Weakly Supervised Person Search with Region Siamese Networks
Supervised learning is dominant in person search, but it requires elaborate labeling of bounding boxes and identities. Large-scale labeled training data is often difficult to collect, especially for person identities. A …
Contrastive LearningPerson SearchDiscrepant 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-Identification