Dense Learning based Semi-Supervised Object Detection

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 detecto...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 4805 - 4814
Hlavní autoři: Chen, Binghui, Li, Pengyu, Chen, Xiang, Wang, Biao, Zhang, Lei, Hua, Xian-Sheng
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2022
Témata:
Bridges
categorization
Codes
Computer vision
Detectors
Filtering
grouping and shape analysis; Self-& semi-& meta- & unsupervised learning
Recognition: detection
retrieval; Deep learning architectures and techniques; Scene analysis and understanding; Segmentation
Training
Uncertainty
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.00477