activity
20162020
most citedKaoKore: A Pre-modern Japanese Art Facial Expression Dataset

14 citations · 41 across the 7 of their papers we have counts for

collaborators

11 papers

cs.LG20206 cited

Jigsaw-VAE: Towards Balancing Features in Variational Autoencoders

Saeid Asgari Taghanaki, Mohammad Havaei, Alex Lamb +3

The latent variables learned by VAEs have seen considerable interest as an unsupervised way of extracting features, which can then be used for downstream tasks. There is a growing…

cs.CV202014 cited

KaoKore: A Pre-modern Japanese Art Facial Expression Dataset

Yingtao Tian, Chikahiko Suzuki, Tarin Clanuwat +3

From classifying handwritten digits to generating strings of text, the datasets which have received long-time focus from the machine learning community vary greatly in their subjec…

cs.CV2019

SketchTransfer: A Challenging New Task for Exploring Detail-Invariance and the Abstractions Learned by Deep Networks

Alex Lamb, Sherjil Ozair, Vikas Verma +1

Deep networks have achieved excellent results in perceptual tasks, yet their ability to generalize to variations not seen during training has come under increasing scrutiny. In thi…

cs.CV20198 cited

KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning

Tarin Clanuwat, Alex Lamb, Asanobu Kitamoto

Kuzushiji, a cursive writing style, had been used in Japan for over a thousand years starting from the 8th century. Over 3 millions books on a diverse array of topics, such as lite…

cs.LG2019

State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations

Alex Lamb, Jonathan Binas, Anirudh Goyal +5

Machine learning promises methods that generalize well from finite labeled data. However, the brittleness of existing neural net approaches is revealed by notable failures, such as…

stat.ML2019

On Adversarial Mixup Resynthesis

Christopher Beckham, Sina Honari, Vikas Verma +5

In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We explore models that are capable of combining the a…