Pseudo Label Filtering
7 papers with code • 0 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in Pseudo Label Filtering
Most implemented papers
Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering
Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available and instant inference on target domain is required.
Unsupervised domain adaptation semantic segmentation of high-resolution remote sensing imagery with invariant domain-level prototype memory
RS-CSU/MemoryAdaptNet-master
•
•
This study proposes a novel unsupervised domain adaptation semantic segmentation network (MemoryAdaptNet) for the semantic segmentation of HRS imagery.
Pseudo-Label Noise Suppression Techniques for Semi-Supervised Semantic Segmentation
christmasfan/ssl_denoising_segmentation
•
•
Current SSL approaches use an initially supervised trained model to generate predictions for unlabelled images, called pseudo-labels, which are subsequently used for training a new model from scratch.
Probabilistic Domain Adaptation for Biomedical Image Segmentation
computational-cell-analytics/probabilistic-domain-adaptation
•
•
We further study joint and separate source-target training strategies and evaluate our method on three challenging domain adaptation tasks for biomedical segmentation.
Semi-Supervised Semantic Segmentation With Region Relevance
nust-machine-intelligence-laboratory/torchsemiseg2
•
•
The most common approach is to generate pseudo-labels for unlabeled images to augment the training data.
FishSegSSL: A Semi-Supervised Semantic Segmentation Framework for Fish-Eye Images
snehaputul/FishSegSSL
•
•
Journal of Imaging 2024
In this study, we explore and benchmark two popular semi-supervised methods from the perspective image domain for fish-eye image segmentation.
Uncertainty-Aware Pseudo-Label Filtering for Source-Free Unsupervised Domain Adaptation
chenxi52/upa
•
•
Source-free unsupervised domain adaptation (SFUDA) aims to enable the utilization of a pre-trained source model in an unlabeled target domain without access to source data.
