Direct domain adaptation through reciprocal linear transformations

08/17/2021
by   Tariq Alkhalifah, et al.
11

We propose a direct domain adaptation (DDA) approach to enrich the training of supervised neural networks on synthetic data by features from real-world data. The process involves a series of linear operations on the input features to the NN model, whether they are from the source or target domains, as follows: 1) A cross-correlation of the input data (i.e. images) with a randomly picked sample pixel (or pixels) of all images from that domain or the mean of all randomly picked sample pixel (or pixels) of all images. 2) The convolution of the resulting data with the mean of the autocorrelated input images from the other domain. In the training stage, as expected, the input images are from the source domain, and the mean of auto-correlated images are evaluated from the target domain. In the inference/application stage, the input images are from the target domain, and the mean of auto-correlated images are evaluated from the source domain. The proposed method only manipulates the data from the source and target domains and does not explicitly interfere with the training workflow and network architecture. An application that includes training a convolutional neural network on the MNIST dataset and testing the network on the MNIST-M dataset achieves a 70 component analysis (PCA), as well as t-SNE, show that the input features from the source and target domains, after the proposed direct transformations, share similar properties along with the principal components as compared to the original MNIST and MNIST-M input features.

READ FULL TEXT

page 5

page 7

page 10

page 11

page 12

page 15

research
05/25/2020

Contradistinguisher: Applying Vapnik's Philosophy to Unsupervised Domain Adaptation

A complex combination of simultaneous supervised-unsupervised learning i...
research
09/11/2021

MLReal: Bridging the gap between training on synthetic data and real data applications in machine learning

Among the biggest challenges we face in utilizing neural networks traine...
research
02/08/2018

Transductive Adversarial Networks (TAN)

Transductive Adversarial Networks (TAN) is a novel domain-adaptation mac...
research
11/20/2020

Seismic Facies Analysis: A Deep Domain Adaptation Approach

Deep neural networks (DNNs) can learn accurately from large quantities o...
research
09/21/2014

Domain Adaptive Neural Networks for Object Recognition

We propose a simple neural network model to deal with the domain adaptat...
research
01/07/2020

Missing-Class-Robust Domain Adaptation by Unilateral Alignment for Fault Diagnosis

Domain adaptation aims at improving model performance by leveraging the ...
research
11/15/2022

Dynamic-Pix2Pix: Noise Injected cGAN for Modeling Input and Target Domain Joint Distributions with Limited Training Data

Learning to translate images from a source to a target domain with appli...

Please sign up or login with your details

Forgot password? Click here to reset