Search Results for author:
Found 19 papers, 8 papers with code
Leveraging Old Knowledge to Continually Learn New Classes in Medical Images
Class-incremental continual learning is a core step towards developing artificial intelligence systems that can continuously adapt to changes in the environment by learning new concepts without forgetting those previously learned.
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
To replicate the success of text-to-image (T2I) generation, recent works employ large-scale video datasets to train a text-to-video (T2V) generator.
A Deep Learning Approach to Generating Photospheric Vector Magnetograms of Solar Active Regions for SOHO/MDI Using SDO/HMI and BBSO Data
We propose a new deep learning method, named MagNet, to learn from combined LOS magnetograms, Bx and By taken by SDO/HMI along with H-alpha observations collected by the Big Bear Solar Observatory (BBSO), and to generate vector components Bx' and By', which would form vector magnetograms with observed LOS data.
Inferring Line-of-Sight Velocities and Doppler Widths from Stokes Profiles of GST/NIRIS Using Stacked Deep Neural Networks
Obtaining high-quality magnetic and velocity fields through Stokes inversion is crucial in solar physics.
Label-Efficient Online Continual Object Detection in Streaming Video
To thrive in evolving environments, humans are capable of continual acquisition and transfer of new knowledge, from a continuous video stream, with minimal supervisions, while retaining previously learnt experiences.
Explanation-based Data Augmentation for Image Classification
This work proposes a framework that utilizes concept-based explanations to automatically augment the dataset with new images that can cover these under-represented regions to improve the model performance.
PERSONALIZED LAB TEST RESPONSE PREDICTION WITH KNOWLEDGE AUGMENTATION
Further, we model the drug-lab interactions and diagnosis-lab interactions in the form of graphs and design a knowledge-augmented approach to predict patients’ response to a target lab result.
Distributional Shifts in Automated Diabetic Retinopathy Screening
Deep learning-based models are developed to automatically detect if a retina image is `referable' in diabetic retinopathy (DR) screening.
Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies
To some extent, current deep learning solutions can address these challenges.
Towards Fully Interpretable Deep Neural Networks: Are We There Yet?
Despite the remarkable performance, Deep Neural Networks (DNNs) behave as black-boxes hindering user trust in Artificial Intelligence (AI) systems.
Improving Evidence Retrieval for Automated Explainable Fact-Checking
Automated fact-checking on a large-scale is a challenging task that has not been studied systematically until recently.
Towards Bridging the gap between Empirical and Certified Robustness against Adversarial Examples
In this paper, we propose a novel method, called \emph{Certification through Adaptation}, that transforms an AT model into a randomized smoothing classifier during inference to provide certified robustness for $\ell_2$ norm without affecting their empirical robustness against adversarial attacks.
Comprehensible Convolutional Neural Networks via Guided Concept Learning
Learning concepts that are consistent with human perception is important for Deep Neural Networks to win end-user trust.
Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples
Among existing uncertainty estimation approaches, Dirichlet Prior Network (DPN) distinctly models different predictive uncertainty types.
PREMIER: Personalized REcommendation for Medical prescrIptions from Electronic Records
In this work, we design a two-stage attention-based personalized medication recommender system called PREMIER which incorporates information from the EHR to suggest a set of medications.
Approximate Manifold Defense Against Multiple Adversarial Perturbations
Using adversarial training to defend against multiple types of perturbation requires expensive adversarial examples from different perturbation types at each training step.
Normal Similarity Network for Generative Modelling
Gaussian distributions are commonly used as a key building block in many generative models.
Author-aware Aspect Topic Sentiment Model to Retrieve Supporting Opinions from Reviews
User generated content about products and services in the form of reviews are often diverse and even contradictory.
Quantifying Aspect Bias in Ordinal Ratings using a Bayesian Approach
User opinions expressed in the form of ratings can influence an individual's view of an item.
