← Search

Leonard K. M. Poon

2 accepted papers

2023

Two-stage holistic and contrastive explanation of image classification

UAI 2023poster

The need to explain the output of a deep neural network classifier is now widely recognized. While previous methods typically explain a single class in the output, we advocate explaining the whole output, which is a probability distribution over multiple classes. A whole-output explanation can help…

2019

Learning Latent Superstructures in Variational Autoencoders for Deep Multidimensional Clustering

ICLR 2019poster

We investigate a variant of variational autoencoders where there is a superstructure of discrete latent variables on top of the latent features. In general, our superstructure is a tree structure of multiple super latent variables and it is automatically learned from data. When there is only one lat…

Cited by 75SourcePDFScholar