AdapterNet - learning input transformation for domain adaptation

05/29/2018
by   Alon Hazan, et al.
0

Deep neural networks have demonstrated impressive performance in various machine learning tasks. However, they are notoriously sensitive to changes in data distribution. Often, even a slight change in the distribution can lead to drastic performance reduction. Artificially augmenting the data may help to some extent, but in most cases, fails to achieve model invariance to the data distribution. Some examples where this sub-class of domain adaptation can be valuable are various imaging modalities such as thermal imaging, X-ray, ultrasound, and MRI, where changes in acquisition parameters or acquisition device manufacturer will result in different representation of the same input. Our work shows that standard finetuning fails to adapt the model in certain important cases. We propose a novel method of adapting to a new data source, and demonstrate near perfect adaptation on a customized ImageNet benchmark.

READ FULL TEXT

page 4

page 5

page 6

research
03/01/2022

Low-Cost On-device Partial Domain Adaptation (LoCO-PDA): Enabling efficient CNN retraining on edge devices

With the increased deployment of Convolutional Neural Networks (CNNs) on...
research
12/04/2018

Towards Continuous Domain adaptation for Healthcare

Deep learning algorithms have demonstrated tremendous success on challen...
research
02/09/2020

Domain Adaptation As a Problem of Inference on Graphical Models

This paper is concerned with data-driven unsupervised domain adaptation,...
research
04/24/2020

A survey on domain adaptation theory

All famous machine learning algorithms that correspond to both supervise...
research
11/02/2019

Fair Predictors under Distribution Shift

Recent work on fair machine learning adds to a growing set of algorithmi...
research
08/02/2021

Domain Adaptation for Autoencoder-Based End-to-End Communication Over Wireless Channels

The problem of domain adaptation conventionally considers the setting wh...
research
06/19/2019

Domain Adaptation for Enterprise Email Search

In the enterprise email search setting, the same search engine often pow...

Please sign up or login with your details

Forgot password? Click here to reset