Deep Generative Models, and Data Augmentation, Labelling, and Imperfections
Description
DG4MICCAI 2021 accepted 12 papers from the 17 submissions received. The workshop focusses on recent algorithmic developments, new results, and promising future directions in Deep Generative Models. Deep generative models such as Generative Adversarial Network (GAN) and Variational Auto-Encoder (VAE) are currently receiving widespread attention from not only the computer vision and machine learning communities, but also in the MIC and CAI community.
For DALI 2021, 15 papers from 32 submissions were accepted for publication. They focus on rigorousstudy of medical data related to machine learning systems.
More details
Other editions
Additional editions
Content
DGM4MICCAI 2021 - Image-to-Image Translation, Synthesis.- Frequency-Supervised MRI-to-CT Image Synthesis.- Ultrasound Variational Style Transfer to Generate Images Beyond the Observed Domain.- 3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images.- Bridging the gap between paired and unpaired medical image translation.- Conditional generation of medical images via disentangled adversarial inference. -CT-SGAN: Computed Tomography Synthesis GAN.- Hierarchical Probabilistic Ultrasound Image Inpainting via Variational Inference.- CaCL: class-aware codebook learning for weakly supervised segmentation on diffuse image patterns.- BrainNetGAN: Data augmentation of brain connectivity using generative adversarial network for dementia classification.- Evaluating GANs in medical imaging.- DGM4MICCAI 2021 - AdaptOR challenge.- Improved Heatmap-based Landmark Detection.- Cross-domain Landmarks Detection in Mitral Regurgitation.- DALI2021.- Scalable Semi-supervised Landmark Localization for X-ray Images using Few-shot Deep Adaptive Graph.- Semi-supervised Surgical Tool Detection Based on Highly Confident Pseudo Labeling and Strong Augmentation Driven Consistency.- One-shot Learning for Landmarks Detection.- Compound Figure Separation of Biomedical Images with Side Loss.- Data Augmentation with Variational Autoencoders and Manifold Sampling.- Medical image segmentation with imperfect 3D bounding boxes.- Automated Iterative Label Transfer Improves Segmentation of Noisy Cells in Adaptive Optics Retinal Images.- How Few Annotations are Needed for Segmentation using a Multi-planar U-Net?.- FS-Net: A New Paradigm of Data Expansion for Medical Image Segmentation.- An Efficient Data Strategy for the Detection of Brain Aneurysms from MRA with Deep Learning.- Evaluation of Active Learning Techniques on Medical Image Classification with Unbalanced Data Distributions.- Zero-Shot Domain Adaptation in CT Segmentation by Filtered Back Projection Augmentation.- Label Noise in Segmentation Networks : Mitigation Must Deal with Bias.- DeepMCAT: Large-Scale Deep Clustering for Medical Image Categorization.- MetaHistoSeg: A Python Framework for Meta Learning in Histopathology Image Segmentation.
