Unsupervised task design enables meta-training of medical image classifiers that, after fine-tuning, outperforms other pre-training methods and matches hand-designed task meta-training on a breast DCE-MRI dataset.
Journal of computational and applied mathematics (1987)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
Low-rank additive experts with dual-scale gating and threat-guided diversification improve multi-perturbation adversarial robustness by routing different threat types through distinct model pathways.
citing papers explorer
-
Unsupervised Task Design to Meta-Train Medical Image Classifiers
Unsupervised task design enables meta-training of medical image classifiers that, after fine-tuning, outperforms other pre-training methods and matches hand-designed task meta-training on a breast DCE-MRI dataset.
-
RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbations
Low-rank additive experts with dual-scale gating and threat-guided diversification improve multi-perturbation adversarial robustness by routing different threat types through distinct model pathways.