דלג לתוכן (מקש קיצור 's')
Logo of Technion
Logo of CS Department
אירועים

אירועים

Pixel Club: One-Sided Unsupervised Domain Mapping via Distance Correlations
event speaker icon
שגיא בן-נעים (אונ' תל-אביב)
event date icon
יום שלישי, 16.1.2018, 11:30
event location icon
חדר 337, בניין טאוב למדעי המחשב
In unsupervised domain mapping, the learner is given two unmatched datasets A and B. The goal is to learn a mapping G_AB that translates a sample in A to the analog sample in B. Recent approaches have shown that when learning simultaneously both G_AB and the inverse mapping G_BA, convincing mappings are obtained. In this work, we present a method of learning G_AB without learning G_BA. This is done by learning a mapping that maintains the distance between a pair of samples. Moreover, good mappings are obtained, even by maintaining the distance between different parts of the same sample before and after mapping. We present experimental results that the new method not only allows for one sided mapping learning, but also leads to preferable numerical results over the existing circularity-based constraint.
[בחזרה לאינדקס האירועים]