Timezone: »

 
Poster
Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation
Kaichao You · Ximei Wang · Mingsheng Long · Michael Jordan

Wed Jun 12 06:30 PM -- 09:00 PM (PDT) @ Pacific Ballroom #259
in Posters Wed »

Deep unsupervised domain adaptation (Deep UDA) methods successfully leverage rich labeled data in a source domain to boost the performance on related but unlabeled data in a target domain. However, algorithm comparison is cumbersome in Deep UDA due to the absence of accurate and standardized model selection method, posing an obstacle to further advances in the field. Existing model selection methods for Deep UDA are either highly biased, restricted, unstable, or even controversial (requiring labeled target data). To this end, we propose Deep Embedded Validation (DEV), which embeds adapted feature representation into the validation procedure to obtain unbiased estimation of the target risk with bounded variance. The variance is further reduced by the technique of control variate. The efficacy of the method has been justified both theoretically and empirically.

Keywords: Transfer and Multitask Learning

Author Information

Kaichao You (Tsinghua University)
Ximei Wang (Tsinghua University)
Mingsheng Long (Tsinghua University)
Michael Jordan (UC Berkeley)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors