Reconstructing Domain-Specific Features for Unsupervised Domain-Adaptive Object Detection

Reconstructing Domain-Specific Features for Unsupervised Domain-Adaptive Object Detection

Unsupervised domain adaptation (UDA) effectively transfers knowledge learned from a labeled source domain to an unlabeled target domain. The teacher–student framework, which generates pseudo-labels for target domain samples and uses them for pseudo-supervised training, enables self-training and impr...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuai Dong, Kang Deng, Kun Zou
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Information
Subjects:
one-stage object detection
domain adaptation
domain-specific head
teacher–student framework
feature reconstruction
unreliable pseudo-labels
Online Access:https://www.mdpi.com/2078-2489/16/6/439
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items

Similar Items