Recognition in Unseen Domains: Domain Generalization via Universal Non-volume Preserving Models

05/28/2019
by   Thanh-Dat Truong, et al.
0

Recognition across domains has recently become an active topic in the research community. However, it has been largely overlooked in the problem of recognition in new unseen domains. Under this condition, the delivered deep network models are unable to be updated, adapted or fine-tuned. Therefore, recent deep learning techniques, such as: domain adaptation, feature transferring, and fine-tuning, cannot be applied. This paper presents a novel approach to the problem of domain generalization in the context of deep learning. The proposed method is evaluated on different datasets in various problems, i.e. (i) digit recognition on MNIST, SVHN and MNIST-M, (ii) face recognition on Extended Yale-B, CMU-PIE and CMU-MPIE, and (iii) pedestrian recognition on RGB and Thermal image datasets. The experimental results show that our proposed method consistently improves the performance accuracy. It can be also easily incorporated with any other CNN frameworks within an end-to-end deep network design for object detection and recognition problems to improve their performance.

READ FULL TEXT

page 1

page 2

page 4

page 6

page 8

research
12/09/2018

Beyond Domain Adaptation: Unseen Domain Encapsulation via Universal Non-volume Preserving Models

Recognition across domains has recently become an active topic in the re...
research
05/28/2019

Image Alignment in Unseen Domains via Domain Deep Generalization

Image alignment across domains has recently become one of the realistic ...
research
05/22/2022

OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation

Unsupervised domain adaptation is one of the challenging problems in com...
research
11/06/2016

Domain Adaptation For Formant Estimation Using Deep Learning

In this paper we present a domain adaptation technique for formant estim...
research
04/25/2022

Joint Feature Distribution Alignment Learning for NIR-VIS and VIS-VIS Face Recognition

Face recognition for visible light (VIS) images achieve high accuracy th...
research
01/31/2019

Episodic Training for Domain Generalization

Domain generalization (DG) is the challenging and topical problem of lea...
research
08/15/2019

Deep learning for Plankton and Coral Classification

Oceans are the essential lifeblood of the Earth: they provide over 70 ox...

Please sign up or login with your details

Forgot password? Click here to reset