Domain Adaptation and Representation Transfer
Description
DART 2022 accepted 13 papers from the 25 submissions received. The workshop aims at creating a discussion forum to compare, evaluate, and discuss methodological advancements and ideas that can improve the applicability of machine learning (ML)/deep learning (DL) approaches to clinical setting by making them robust and consistent across different domains.
More details
Other editions
Additional editions
Content
Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification.- Benchmarking Transformers for Medical Image Classification.- Supervised domain adaptation using gradients transfer for improved medical image analysis.- Stain-AgLr: Stain Agnostic Learning for Computational Histopathology using Domain Consistency and Stain Regeneration Loss.- MetaMedSeg: Volumetric Meta-learning for Few-Shot Organ Segmentation.- Unsupervised site adaptation by intra-site variability alignment.- Discriminative, Restorative, and Adversarial Learning: Stepwise Incremental Pretraining.- POPAR: Patch Order Prediction and Appearance Recovery for Self-supervised Medical Image Analysis.- Feather-Light Fourier Domain Adaptation in Magnetic Resonance Imaging.- Seamless Iterative Semi-Supervised Correction of Imperfect Labels in Microscopy Images.- Task-agnostic Continual Hippocampus Segmentation for Smooth Population Shifts.- Adaptive Optimization with Fewer Epochs Improves Across-Scanner Generalization of U-Net based Medical Image Segmentation.- CateNorm: Categorical Normalization for Robust Medical Image Segmentation.
