DeepAI
Log In Sign Up

Joint Geometrical and Statistical Alignment for Visual Domain Adaptation

05/16/2017
by   Jing Zhang, et al.
0

This paper presents a novel unsupervised domain adaptation method for cross-domain visual recognition. We propose a unified framework that reduces the shift between domains both statistically and geometrically, referred to as Joint Geometrical and Statistical Alignment (JGSA). Specifically, we learn two coupled projections that project the source domain and target domain data into low dimensional subspaces where the geometrical shift and distribution shift are reduced simultaneously. The objective function can be solved efficiently in a closed form. Extensive experiments have verified that the proposed method significantly outperforms several state-of-the-art domain adaptation methods on a synthetic dataset and three different real world cross-domain visual recognition tasks.

READ FULL TEXT
05/25/2020

Contradistinguisher: Applying Vapnik's Philosophy to Unsupervised Domain Adaptation

A complex combination of simultaneous supervised-unsupervised learning i...
02/12/2020

Bi-Directional Generation for Unsupervised Domain Adaptation

Unsupervised domain adaptation facilitates the unlabeled target domain r...
10/23/2020

Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation

Domain adaptation (DA) becomes an up-and-coming technique to address the...
10/13/2021

Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment

Eliminating the covariate shift cross domains is one of the common metho...
09/05/2015

Unsupervised Cross-Domain Recognition by Identifying Compact Joint Subspaces

This paper introduces a new method to solve the cross-domain recognition...
03/14/2022

Bures Joint Distribution Alignment with Dynamic Margin for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) is one of the prominent tasks of tr...
06/07/2022

Searching for Optimal Subword Tokenization in Cross-domain NER

Input distribution shift is one of the vital problems in unsupervised do...