Pseudo Labels

Weak-Mamba-UNet: How CNN, ViT, and Visual Mamba Collaborate to Segment Medical Images from Scribbles

Weak-Mamba-UNet: How CNN, ViT, and Visual Mamba Collaborate to Segment Medical Images from Scribbles

Weak-Mamba-UNet: How CNN, ViT, and Visual Mamba Collaborate to Segment Medical Images from Scribbles | AI Trend Blend AITrendBlend Machine Learning Computer Vision About Medical AI & Weakly-Supervised Learning · arXiv:2402.10887 · University of Oxford / Mianyang Visual Engineering Center · 25 min read Teaching Three Different Brains to Agree — How Weak-Mamba-UNet Segments Hearts […]

Weak-Mamba-UNet: How CNN, ViT, and Visual Mamba Collaborate to Segment Medical Images from Scribbles Read More »

IERE: SAM-Powered Cross-Domain Medical Image Segmentation Without Inference Cost

IERE: SAM-Powered Cross-Domain Medical Image Segmentation Without Inference Cost

IERE: SAM-Powered Cross-Domain Medical Image Segmentation Without Inference Cost | AI Trend Blend AITrendBlend Machine Learning Computer Vision Image Segmentation About Medical AI · Segmentation · Pattern Recognition, Vol. 179 (2026) · 17 min read IERE: Teaching a Small Medical Segmentation Model to Generalize Using SAM — Only During Training Researchers at Ruijin Hospital and

IERE: SAM-Powered Cross-Domain Medical Image Segmentation Without Inference Cost Read More »

How Bidirectional Copy-Paste Closes the Labeled Unlabeled Gap

How Bidirectional Copy-Paste Closes the Labeled Unlabeled Gap

Analysis by the aitrendblend editorial team, filed under AI for Medical Imaging and Healthcare About a 17 minute read Semi Supervised Segmentation Mean Teacher Cardiac MRI Pancreatic CT Copy Paste Augmentation A copy paste blend between a labeled and an unlabeled scan, the core mechanism behind bidirectional copy paste segmentation A hospital research team has

How Bidirectional Copy-Paste Closes the Labeled Unlabeled Gap Read More »

KD-FixMatch Fixes FixMatch's Noisy Early Pseudo Labels.

KD-FixMatch Fixes FixMatch’s Noisy Early Pseudo Labels

Knowledge Distillation Semi Supervised Learning 8 min read Analysis by the aitrendblend editorial team An outer network’s best guesses become the inner network’s head start, once they clear two separate filters. A retailer sorting product photos into defective and acceptable piles runs into a wall almost every computer vision team eventually hits. Good images are

KD-FixMatch Fixes FixMatch’s Noisy Early Pseudo Labels Read More »

Long Tailed Weights Beat Thresholds For Pseudo Labels

Analysis by the aitrendblend editorial team · Probabilistic methods · Source paper posted March 2025 Semi Supervised Learning Uncertainty Estimation Ensemble Learning Pose Estimation Pseudo Labels Instead of relying on a hard confidence cutoff, UES introduces long tailed weights derived from ensemble uncertainty, ensuring even the least trustworthy pseudo labels still contribute valuable signal to

Long Tailed Weights Beat Thresholds For Pseudo Labels Read More »