[This corrects the article DOI: 10.1371/journal.pone.0250281.].
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10289315 | PMC |
| http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0287802 | PLOS |
Publication Analysis
Top Keywords
Similar Publications
SURABHI: Self-Training Using Rectified Annotations-Based Hard Instances for Eidetic Cattle Recognition.
Sensors (Basel)
November 2024
School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA.
We propose a self-training scheme, SURABHI, that trains deep-learning keypoint detection models on machine-annotated instances, together with the methodology to generate those instances. SURABHI aims to improve the keypoint detection accuracy not by altering the structure of a deep-learning-based keypoint detector model but by generating highly effective training instances. The machine-annotated instances used in SURABHI are hard instances-instances that require a rectifier to correct the keypoints misplaced by the keypoint detection model.
View Article and Find Full Text PDFA Curriculum-Style Self-Training Approach for Source-Free Semantic Segmentation.
IEEE Trans Pattern Anal Mach Intell
December 2024
Source-free domain adaptation has developed rapidly in recent years, where the well-trained source model is adapted to the target domain instead of the source data, offering the potential for privacy concerns and intellectual property protection. However, a number of feature alignment techniques in prior domain adaptation methods are not feasible in this challenging problem setting. Thereby, we resort to probing inherent domain-invariant feature learning and propose a curriculum-style self-training approach for source-free domain adaptive semantic segmentation.
View Article and Find Full Text PDFOTAMatch: Optimal Transport Assignment with PseudoNCE for Semi-supervised Learning.
IEEE Trans Image Process
July 2024
In semi-supervised learning (SSL), many approaches follow the effective self-training paradigm with consistency regularization, utilizing threshold heuristics to alleviate label noise. However, such threshold heuristics lead to the underutilization of crucial discriminative information from the excluded data. In this paper, we present OTAMatch, a novel SSL framework that reformulates pseudo-labeling as an optimal transport (OT) assignment problem and simultaneously exploits data with high confidence to mitigate the confirmation bias.
View Article and Find Full Text PDFUnsupervised domain adaptation multi-level adversarial learning-based crossing-domain retinal vessel segmentation.
Comput Biol Med
August 2024
Department of Geriatrics, The Second Xiangya Hospital of Central South University, Changsha, 410011, China. Electronic address:
Background: The retinal vasculature, a crucial component of the human body, mirrors various illnesses such as cardiovascular disease, glaucoma, and retinopathy. Accurate segmentation of retinal vessels in funduscopic images is essential for diagnosing and understanding these conditions. However, existing segmentation models often struggle with images from different sources, making accurate segmentation in crossing-source fundus images challenging.
View Article and Find Full Text PDFA Robust Semi-Supervised Broad Learning System Guided by Ensemble-Based Self-Training.
IEEE Trans Cybern
November 2024
Broad learning system (BLS) with semi-supervised learning relieves label dependence and expands application. Despite some efforts and progress, the semi-supervised BLS still needs improvement, especially in handling imbalanced data or concept drift scenarios for self-training-based methods. To this extent, this article proposes a robust semi-supervised BLS guided by ensemble-based self-training (ESTSS-BLS).
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!