Search Results for author: Wynne Hsu

Found 19 papers, 8 papers with code

Leveraging Old Knowledge to Continually Learn New Classes in Medical Images

1 code implementation24 Mar 2023 Evelyn Chee, Mong Li Lee, Wynne Hsu

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.

Continual Learning

Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

2 code implementations22 Dec 2022 Jay Zhangjie Wu, Yixiao Ge, Xintao Wang, Weixian Lei, YuChao Gu, Yufei Shi, Wynne Hsu, Ying Shan, XiaoHu Qie, Mike Zheng Shou

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.

Style Transfer Text-to-Video Generation +1

A Deep Learning Approach to Generating Photospheric Vector Magnetograms of Solar Active Regions for SOHO/MDI Using SDO/HMI and BBSO Data

no code implementations4 Nov 2022 Haodi Jiang, Qin Li, Zhihang Hu, Nian Liu, Yasser Abduallah, Ju Jing, Genwei Zhang, Yan Xu, Wynne Hsu, Jason T. L. Wang, Haimin Wang

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.

Label-Efficient Online Continual Object Detection in Streaming Video

1 code implementation1 Jun 2022 Jay Zhangjie Wu, David Junhao Zhang, Wynne Hsu, Mengmi Zhang, Mike Zheng Shou

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.

Continual Learning Hippocampus +2

Explanation-based Data Augmentation for Image Classification

1 code implementation NeurIPS 2021 Sandareka Wickramanayake, Wynne Hsu, Mong Li Lee

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.

Classification Data Augmentation +1


no code implementations29 Sep 2021 Suman Bhoi, Mong-Li Lee, Wynne Hsu, Hao Sen Andrew Fang, Ngiap Chuan Tan

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

no code implementations25 Jul 2021 Jay Nandy, Wynne Hsu, Mong Li Lee

Deep learning-based models are developed to automatically detect if a retina image is `referable' in diabetic retinopathy (DR) screening.


Towards Fully Interpretable Deep Neural Networks: Are We There Yet?

no code implementations24 Jun 2021 Sandareka Wickramanayake, Wynne Hsu, Mong Li Lee

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

1 code implementation NAACL 2021 Chris Samarinas, Wynne Hsu, Mong Li Lee

Automated fact-checking on a large-scale is a challenging task that has not been studied systematically until recently.

Fact Checking Retrieval

Towards Bridging the gap between Empirical and Certified Robustness against Adversarial Examples

no code implementations9 Feb 2021 Jay Nandy, Sudipan Saha, Wynne Hsu, Mong Li Lee, Xiao Xiang Zhu

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.

Adversarial Robustness

Comprehensible Convolutional Neural Networks via Guided Concept Learning

1 code implementation11 Jan 2021 Sandareka Wickramanayake, Wynne Hsu, Mong Li Lee

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

1 code implementation NeurIPS 2020 Jay Nandy, Wynne Hsu, Mong Li Lee

Among existing uncertainty estimation approaches, Dirichlet Prior Network (DPN) distinctly models different predictive uncertainty types.

Out of Distribution (OOD) Detection

PREMIER: Personalized REcommendation for Medical prescrIptions from Electronic Records

no code implementations28 Aug 2020 Suman Bhoi, Lee Mong Li, Wynne Hsu

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.

Recommendation Systems

Approximate Manifold Defense Against Multiple Adversarial Perturbations

2 code implementations5 Apr 2020 Jay Nandy, Wynne Hsu, Mong Li Lee

Using adversarial training to defend against multiple types of perturbation requires expensive adversarial examples from different perturbation types at each training step.

Adversarial Robustness Image Classification

Normal Similarity Network for Generative Modelling

no code implementations14 May 2018 Jay Nandy, Wynne Hsu, Mong Li Lee

Gaussian distributions are commonly used as a key building block in many generative models.

Density Estimation Image Generation

Quantifying Aspect Bias in Ordinal Ratings using a Bayesian Approach

no code implementations15 May 2017 Lahari Poddar, Wynne Hsu, Mong Li Lee

User opinions expressed in the form of ratings can influence an individual's view of an item.

Bayesian Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.