Search Results for author:
Found 10 papers, 7 papers with code
An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization
In this work, we extend the globally-aware multiple instance classifier, a framework we proposed to address these unique properties of medical images.
Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning
Existing unsupervised video-to-video translation methods fail to produce translated videos which are frame-wise realistic, semantic information preserving and video-level consistent.
Weakly-supervised High-resolution Segmentation of Mammography Images for Breast Cancer Diagnosis
In cancer diagnosis, interpretability can be achieved by localizing the region of the input image responsible for the output, i. e. the location of a lesion.
Cramér-Rao bound-informed training of neural networks for quantitative MRI
We find, however, that in heterogeneous parameter spaces, i. e. in spaces in which the variance of the estimated parameters varies considerably, good performance is hard to achieve and requires arduous tweaking of the loss function, hyper parameters, and the distribution of the training data in parameter space.
Adaptive Early-Learning Correction for Segmentation from Noisy Annotations
We discover a phenomenon that has been previously reported in the context of classification: the networks tend to first fit the clean pixel-level labels during an "early-learning" phase, before eventually memorizing the false annotations.
Sequence-to-Sequence Modeling for Action Identification at High Temporal Resolution
To address this, we propose a novel approach for high-resolution action identification, inspired by speech-recognition techniques, which is based on a sequence-to-sequence model that directly predicts the sequence of actions.
Are All Losses Created Equal: A Neural Collapse Perspective
We extend such results and show through global solution and landscape analyses that a broad family of loss functions including commonly used label smoothing (LS) and focal loss (FL) exhibits Neural Collapse.
Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning
The framework employs a novel self-paced sampling strategy to ensure the accuracy of pseudo labels.
Controllable One-Shot Face Video Synthesis With Semantic Aware Prior
The one-shot talking-head synthesis task aims to animate a source image to another pose and expression, which is dictated by a driving frame.
Quantifying Impairment and Disease Severity Using AI Models Trained on Healthy Subjects
We applied the COBRA score to address a key limitation of current clinical evaluation of upper-body impairment in stroke patients.
