Unsupervised Domain Adaptation using Generative Models and Self-ensembling

12/02/2018
by   Eman T. Hassan, et al.
0

Transferring knowledge across different datasets is an important approach to successfully train deep models with a small-scale target dataset or when few labeled instances are available. In this paper, we aim at developing a model that can generalize across multiple domain shifts, so that this model can adapt from a single source to multiple targets. This can be achieved by randomizing the generation of the data of various styles to mitigate the domain mismatch. First, we present a new adaptation to the CycleGAN model to produce stochastic style transfer between two image batches of different domains. Second, we enhance the classifier performance by using a self-ensembling technique with a teacher and student model to train on both original and generated data. Finally, we present experimental results on three datasets Office-31, Office-Home, and Visual Domain adaptation. The results suggest that selfensembling is better than simple data augmentation with the newly generated data and a single model trained this way can have the best performance across all different transfer tasks.

READ FULL TEXT

page 2

page 4

page 6

page 7

page 8

research
03/31/2023

One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models

Adapting a segmentation model from a labeled source domain to a target d...
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
06/16/2022

CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains

Unsupervised Domain Adaptation demonstrates great potential to mitigate ...
research
06/06/2018

A Comparative Study on Unsupervised Domain Adaptation Approaches for Coffee Crop Mapping

In this work, we investigate the application of existing unsupervised do...
research
10/08/2015

Simultaneous Deep Transfer Across Domains and Tasks

Recent reports suggest that a generic supervised deep CNN model trained ...
research
01/27/2022

Controlling Directions Orthogonal to a Classifier

We propose to identify directions invariant to a given classifier so tha...
research
05/29/2019

d-SNE: Domain Adaptation using Stochastic Neighborhood Embedding

Deep neural networks often require copious amount of labeled-data to tra...

Please sign up or login with your details

Forgot password? Click here to reset