A multitask learning method with instance-aware pseudo-labeling and class-focused contrastive learning outperforms prior UDA and WDA techniques for weakly supervised domain-adaptive mitochondria segmentation in EM images.
Domain adaptation for medical image analysis: a survey
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
The work introduces a residual noise learning framework for cross-dose PET denoising that avoids averaged mappings by estimating noise directly from low-dose inputs and shows gains over one-size-for-all and dose-specific baselines on multi-center data.
citing papers explorer
-
Instance-Aware Pseudo-Labeling and Class-Focused Contrastive Learning for Weakly Supervised Domain Adaptive Segmentation of Electron Microscopy
A multitask learning method with instance-aware pseudo-labeling and class-focused contrastive learning outperforms prior UDA and WDA techniques for weakly supervised domain-adaptive mitochondria segmentation in EM images.
-
Rethinking Cross-Dose PET Denoising: Mitigating Averaging Effects via Residual Noise Learning
The work introduces a residual noise learning framework for cross-dose PET denoising that avoids averaged mappings by estimating noise directly from low-dose inputs and shows gains over one-size-for-all and dose-specific baselines on multi-center data.