Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

dense learning

Dense learning is an approach to computer vision in which a model learns from labels assigned across many spatial locations in an image, rather than only from a small set of object-level labels. In semi-supervised object detection, it uses pixel-wise pseudo-labels—estimated labels for unlabeled images—to train anchor-free detectors.

1 item

Dense Learning based Semi-Supervised Object Detection

Dense Learning based Semi-Supervised Object Detection

Binghui Chen, Pengyu Li, Xiang Chen, Biao Wang, Lei Zhang, Xian-Sheng Hua

OrganizationsAlibaba GroupHong Kong Polytechnic University

Why you should read this

Proposes an anchor-free semi-supervised object detection framework that assigns dense pixel-level pseudo-labels via adaptive filtering and scale-consistent regularization to substantially outperform anchor-based methods on limited labeled data.

Semi-supervised object detection (SSOD) aims to facilitate the training and deployment of object detectors with the help of a large amount of unlabeled data. Though various self-training based and consistency-regularization based SSOD methods have been proposed, most of them are anchor-based detectors, ignoring the fact that in many real-world applications anchor-free detectors are more demanded. In this paper, we intend to bridge this gap and propose a DenSe Learning (DSL) based anchor-free SSOD algorithm. Specifically, we achieve this goal by introducing several novel techniques, including an Adaptive Filtering strategy for assigning multi-level and accurate dense pixel-wise pseudo-labels, an Aggregated Teacher for producing stable and precise pseudo-labels, and an uncertainty-consistency-regularization term among scales and shuffled patches for improving the generalization capability of the detector. Extensive experiments are conducted on MS-COCO and PASCAL-VOC, and the results show that our proposed DSL method records new state-of-the-art SSOD performance, surpassing existing methods by a large margin. Codes can be found at https://github.com/chenbinghui1/DSL.

Added

2026-09-26