How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?

12/30/2020
by   Li Zhong, et al.
9

Unsupervised domain adaptation (UDA) aims to train a target classifier with labeled samples from the source domain and unlabeled samples from the target domain. Classical UDA learning bounds show that target risk is upper bounded by three terms: source risk, distribution discrepancy, and combined risk. Based on the assumption that the combined risk is a small fixed value, methods based on this bound train a target classifier by only minimizing estimators of the source risk and the distribution discrepancy. However, the combined risk may increase when minimizing both estimators, which makes the target risk uncontrollable. Hence the target classifier cannot achieve ideal performance if we fail to control the combined risk. To control the combined risk, the key challenge takes root in the unavailability of the labeled samples in the target domain. To address this key challenge, we propose a method named E-MixNet. E-MixNet employs enhanced mixup, a generic vicinal distribution, on the labeled source samples and pseudo-labeled target samples to calculate a proxy of the combined risk. Experiments show that the proxy can effectively curb the increase of the combined risk when minimizing the source risk and distribution discrepancy. Furthermore, we show that if the proxy of the combined risk is added into loss functions of four representative UDA methods, their performance is also improved.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/19/2019

Open Set Domain Adaptation: Theoretical Bound and Algorithm

Unsupervised domain adaptation for classification tasks has achieved gre...
research
03/26/2020

Unsupervised domain adaptation with exploring more statistics and discriminative information

Unsupervised domain adaptation aims at transferring knowledge from the l...
research
06/23/2020

Bridging the Theoretical Bound and Deep Algorithms for Open Set Domain Adaptation

In the unsupervised open set domain adaptation (UOSDA), the target domai...
research
06/08/2021

Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation

Unsupervised Domain Adaptation (UDA) aims to generalize the knowledge le...
research
06/21/2018

Target Contrastive Pessimistic Discriminant Analysis

Domain-adaptive classifiers learn from a source domain and aim to genera...
research
10/03/2019

A General Upper Bound for Unsupervised Domain Adaptation

In this work, we present a novel upper bound of target error to address ...
research
06/20/2020

Unsupervised Vehicle Re-identification with Progressive Adaptation

Vehicle re-identification (reID) aims at identifying vehicles across dif...

Please sign up or login with your details

Forgot password? Click here to reset