activity
20192022
collaborators

5 papers

cs.CV2022

Embracing Annotation Efficient Learning (AEL) for Digital Pathology and Natural Images

Eu Wern Teh

Jitendra Malik once said, "Supervision is the opium of the AI researcher". Most deep learning techniques heavily rely on extreme amounts of human labels to work effectively. In tod…

cs.CV2022

Understanding the impact of image and input resolution on deep digital pathology patch classifiers

Eu Wern Teh, Graham W. Taylor

We consider annotation efficient learning in Digital Pathology (DP), where expert annotations are expensive and thus scarce. We explore the impact of image and input resolution on…

eess.IV2022

Learning with Less Labels in Digital Pathology via Scribble Supervision from Natural Images

Eu Wern Teh, Graham W. Taylor

A critical challenge of training deep learning models in the Digital Pathology (DP) domain is the high annotation cost by medical experts. One way to tackle this issue is via trans…

cs.CV2020

ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis

Eu Wern Teh, Terrance DeVries, Graham W. Taylor

We consider the problem of distance metric learning (DML), where the task is to learn an effective similarity measure between images. We revisit ProxyNCA and incorporate several en…

cs.CV2019

Learning with less data via Weakly Labeled Patch Classification in Digital Pathology

Eu Wern Teh, Graham W. Taylor

In Digital Pathology (DP), labeled data is generally very scarce due to the requirement that medical experts provide annotations. We address this issue by learning transferable fea…