Domain Confusion with Self Ensembling for Unsupervised Adaptation

10/10/2018
by   Jiawei Wang, et al.
0

Data collection and annotation are time-consuming in machine learning, expecially for large scale problem. A common approach for this problem is to transfer knowledge from a related labeled domain to a target one. There are two popular ways to achieve this goal: adversarial learning and self training. In this article, we first analyze the training unstablity problem and the mistaken confusion issue in adversarial learning process. Then, inspired by domain confusion and self-ensembling methods, we propose a combined model to learn feature and class jointly invariant representation, namely Domain Confusion with Self Ensembling (DCSE). The experiments verified that our proposed approach can offer better performance than empirical art in a variety of unsupervised domain adaptation benchmarks.

READ FULL TEXT
research
08/25/2023

Unsupervised Domain Adaptation for Anatomical Landmark Detection

Recently, anatomical landmark detection has achieved great progresses on...
research
10/09/2018

SPIGAN: Privileged Adversarial Learning from Simulation

Deep Learning for Computer Vision depends mainly on the source of superv...
research
10/16/2019

Unsupervised Domain Adaptation Meets Offline Recommender Learning

To construct a well-performing recommender offline, eliminating selectio...
research
12/21/2019

Unsupervised Domain Adversarial Self-Calibration for Electromyographic-based Gesture Recognition

Surface electromyography (sEMG) provides an intuitive and non-invasive i...
research
02/28/2021

Unsupervised Domain Adaptation for Cross-Subject Few-Shot Neurological Symptom Detection

Modern machine learning tools have shown promise in detecting symptoms o...
research
03/04/2021

Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning

Unsupervised domain adaptation (UDA) typically carries out knowledge tra...
research
12/11/2017

Domain Adaptation Using Adversarial Learning for Autonomous Navigation

Autonomous navigation has become an increasingly popular machine learnin...

Please sign up or login with your details

Forgot password? Click here to reset