research
∙
03/24/2023
Leveraging Old Knowledge to Continually Learn New Classes in Medical Images
Class-incremental continual learning is a core step towards developing a...
share
research
∙
07/25/2021
Distributional Shifts in Automated Diabetic Retinopathy Screening
Deep learning-based models are developed to automatically detect if a re...
research
∙
06/24/2021
Towards Fully Interpretable Deep Neural Networks: Are We There Yet?
Despite the remarkable performance, Deep Neural Networks (DNNs) behave a...
research
∙
02/09/2021
Adversarially Robust Classifier with Covariate Shift Adaptation
Existing adversarially trained models typically perform inference on tes...
research
∙
01/11/2021
Learning Semantically Meaningful Features for Interpretable Classifications
Learning semantically meaningful features is important for Deep Neural N...
research
∙
10/20/2020
Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples
Among existing uncertainty estimation approaches, Dirichlet Prior Networ...
research
∙
04/05/2020
Approximate Manifold Defense Against Multiple Adversarial Perturbations
Existing defenses against adversarial attacks are typically tailored to ...
research
∙
05/14/2018
Normal Similarity Network for Generative Modelling
Gaussian distributions are commonly used as a key building block in many...
research
∙
05/15/2017