Class-Wise Adaptive Strategy for Semi Supervised Semantic Segmentation

Class-Wise Adaptive Strategy for Semi Supervised Semantic Segmentation

Semi-supervised semantic segmentation learns a model for classifying pixels into specific classes using a few labeled samples and numerous unlabeled images. The recent leading approach is consistency regularization by self-training with pseudo-labeling pixels having high confidences for unlabeled im...

Full description

Bibliographic Details
Main Authors: Jingi Ju, Hyeoncheol Noh, Yooseung Wang, Dong-Geol Choi
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Semi-supervised semantic segmentation
over-sampling
confidence threshold
pseudo-labeling
Online Access:https://ieeexplore.ieee.org/document/10423647/

Internet

https://ieeexplore.ieee.org/document/10423647/

Similar Items