Search Results for author:
Found 10 papers, 8 papers with code
Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text
Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the development of network infrastructure.
Pretrained Encoders are All You Need
Data-efficiency and generalization are key challenges in deep learning and deep reinforcement learning as many models are trained on large-scale, domain-specific, and expensive-to-label datasets.
Personalizing Pre-trained Models
Self-supervised or weakly supervised models trained on large-scale datasets have shown sample-efficient transfer to diverse datasets in few-shot settings.
PAL: Intelligence Augmentation using Egocentric Visual Context Detection
We created a wearable system, called PAL, for wearable, personalized, and privacy-preserving egocentric visual context detection.
Uncertainty-Aware Boosted Ensembling in Multi-Modal Settings
Reliability of machine learning (ML) systems is crucial in safety-critical applications such as healthcare, and uncertainty estimation is a widely researched method to highlight the confidence of ML systems in deployment.
Robustness to Missing Features using Hierarchical Clustering with Split Neural Networks
In this work, we propose a simple yet effective approach that clusters similar input features together using hierarchical clustering and then trains proportionately split neural networks with a joint loss.
Uncertainty-Aware Multi-Modal Ensembling for Severity Prediction of Alzheimer's Dementia
Reliability in Neural Networks (NNs) is crucial in safety-critical applications like healthcare, and uncertainty estimation is a widely researched method to highlight the confidence of NNs in deployment.
Why have a Unified Predictive Uncertainty? Disentangling it using Deep Split Ensembles
Our work further demonstrates its applicability in a multi-modal setting using a benchmark Alzheimer's dataset and also shows how deep split ensembles can highlight hidden modality-specific biases.
Multimodal Inductive Transfer Learning for Detection of Alzheimer's Dementia and its Severity
Our system achieves state-of-the-art test accuracy, precision, recall, and F1-score of 83. 3% each for AD classification, and state-of-the-art test root mean squared error (RMSE) of 4. 60 for MMSE score regression.
Real-Time Sleep Staging using Deep Learning on a Smartphone for a Wearable EEG
We present the first real-time sleep staging system that uses deep learning without the need for servers in a smartphone application for a wearable EEG.
