Better object detection by filtering extra unlabeled data with RUPL
Better object detection by filtering extra unlabeled data with RUPL
Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertainty
arXiv paper abstract https://arxiv.org/abs/2212.02747
arXiv PDF paper https://arxiv.org/pdf/2212.02747.pdf
Semi-supervised object detection (SSOD) aims to boost detection performance by leveraging extra unlabeled data.
The teacher-student framework has been shown to be promising for SSOD, in which a teacher network generates pseudo-labels for unlabeled data to assist the training of a student network. Since the pseudo-labels are noisy, filtering the pseudo-labels is crucial
… propose a two-step pseudo-label filtering for the classification and regression heads in a teacher-student framework.
For the classification head, OCL (Object-wise Contrastive Learning) regularizes the object representation learning that utilizes unlabeled data to improve pseudo-label filtering by enhancing the discriminativeness of the classification score.
… For the regression head, … further propose RUPL (Regression-Uncertainty-guided Pseudo-Labeling) to learn the aleatoric uncertainty of object localization for label filtering.
… demonstrate the superiority of … proposed method with competitive performance compared to existing methods.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
