Timezone: »

 
Contrastive Representation Learning with Trainable Augmentation Channel
Masanori Koyama · Kentaro Minami · Takeru Miyato · Yarin Gal

@
in Bayesian Deep Learning »
Event URL: https://openreview.net/forum?id=SOLInSbmbuQ »

In contrastive representation learning, data representation is trained so that it can classify the image instances even when the images are altered by augmentations.However, depending on the datasets, some augmentations can damage the information of the images beyond recognition, and such augmentations can result in collapsed representations.We present a partial solution to this problem by formalizing a stochastic encoding process in which there exist a tug-of-war between the data corruption introduced by the augmentations and the information preserved by the encoder.We show that, with the infoMax objective based on this framework, we can learn a data-dependent distribution of augmentations to avoid the collapse of the representation.

Author Information

Masanori Koyama (Preferred Networks Inc.)
Kentaro Minami (Preferred Networks, Inc.)
Takeru Miyato (Preferred Networks, Inc.)
Yarin Gal (University of Oxford)

More from the Same Authors