Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning

by   Daniel Coelho de Castro, et al.

Revealing latent structure in data is an active field of research, having brought exciting new models such as variational autoencoders and generative adversarial networks, and is essential to push machine learning towards unsupervised knowledge discovery. However, a major challenge is the lack of suitable benchmarks for an objective and quantitative evaluation of learned representations. To address this issue we introduce Morpho-MNIST. We extend the popular MNIST dataset by adding a morphometric analysis enabling quantitative comparison of different models, identification of the roles of latent variables, and characterisation of sample diversity. We further propose a set of quantifiable perturbations to assess the performance of unsupervised and supervised methods on challenging tasks such as outlier detection and domain adaptation.


page 16

page 17


Graph Domain Adaptation: A Generative View

Recent years have witnessed tremendous interest in deep learning on grap...

Latent Space Conditioning on Generative Adversarial Networks

Generative adversarial networks are the state of the art approach toward...

Learning Disentangled Semantic Representation for Domain Adaptation

Domain adaptation is an important but challenging task. Most of the exis...

Increasing the Generalisaton Capacity of Conditional VAEs

We address the problem of one-to-many mappings in supervised learning, w...

Generative Adversarial Networks with Inverse Transformation Unit

In this paper we introduce a new structure to Generative Adversarial Net...

Unsupervised Representation Adversarial Learning Network: from Reconstruction to Generation

A good representation for arbitrarily complicated data should have the c...

Weakly Supervised Representation Learning with Sparse Perturbations

The theory of representation learning aims to build methods that provabl...

Code Repositories


Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning (

view repo