Search Results for author:
Found 10 papers, 5 papers with code
Spatiotemporal Modeling of Multivariate Signals With Graph Neural Networks and Structured State Space Models
Multivariate signals are prevalent in various domains, such as healthcare, transportation systems, and space sciences.
ATCON: Attention Consistency for Vision Models
We propose an unsupervised fine-tuning method that optimizes the consistency of attention maps and show that it improves both classification performance and the quality of attention maps.
TRUST-LAPSE: An Explainable & Actionable Mistrust Scoring Framework for Model Monitoring
We show that our sequential mistrust scores achieve high drift detection rates: over 90% of the streams show < 20% error for all domains.
Domino: Discovering Systematic Errors with Cross-Modal Embeddings
In this work, we address these challenges by first designing a principled evaluation framework that enables a quantitative comparison of SDMs across 1, 235 slice discovery settings in three input domains (natural images, medical images, and time-series data).
Automated Detection of Patients in Hospital Video Recordings
We evaluate an ImageNet pre-trained Mask R-CNN, a standard deep learning model for object detection, on the task of patient detection using our own curated dataset of 45 videos of hospital patients.
TIME-LAPSE: Learning to say “I don't know” through spatio-temporal uncertainty scoring
We show that TIME-LAPSE is more driven by semantic content compared to other methods, i. e., it is more robust to dataset statistics.
Electroencephalogram (EEG)
Out of Distribution (OOD) Detection
+1
Double Descent Optimization Pattern and Aliasing: Caveats of Noisy Labels
Optimization plays a key role in the training of deep neural networks.
Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis
Automated seizure detection and classification from electroencephalography (EEG) can greatly improve seizure diagnosis and treatment.
Semi-Supervised Learning for Sparsely-Labeled Sequential Data: Application to Healthcare Video Processing
We propose a semi-supervised machine learning training strategy to improve event detection performance on sequential data, such as video recordings, when only sparse labels are available, such as event start times without their corresponding end times.
Cross-Modal Data Programming Enables Rapid Medical Machine Learning
Labeling training datasets has become a key barrier to building medical machine learning models.
