Learning Cross-domain Generalizable Features by Representation Disentanglement

02/29/2020
by   Qingjie Meng, et al.
9

Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features in a target domain is an interesting and difficult problem that is rarely discussed in the current literature. This problem is essential for many real-world applications such as improving diagnostic classification or prediction in medical imaging. To address this problem, we propose Mutual-Information-based Disentangled Neural Networks (MIDNet) to extract generalizable features that enable transferring knowledge to unseen categorical features in target domains. The proposed MIDNet is developed as a semi-supervised learning paradigm to alleviate the dependency on labeled data. This is important for practical applications where data annotation requires rare expertise as well as intense time and labor. We demonstrate our method on handwritten digits datasets and a fetal ultrasound dataset for image classification tasks. Experiments show that our method outperforms the state-of-the-art and achieve expected performance with sparsely labeled data.

READ FULL TEXT

page 2

page 7

page 14

page 16

research
09/06/2020

Unsupervised Wasserstein Distance Guided Domain Adaptation for 3D Multi-Domain Liver Segmentation

Deep neural networks have shown exceptional learning capability and gene...
research
07/09/2018

Domain2Vec: Deep Domain Generalization

We address the problem of domain generalization where a decision functio...
research
05/03/2017

Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation

While representation learning aims to derive interpretable features for ...
research
09/03/2018

Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification

We consider the cross-domain sentiment classification problem, where a s...
research
12/16/2020

Towards Recognizing New Semantic Concepts in New Visual Domains

Deep learning models heavily rely on large scale annotated datasets for ...
research
06/23/2023

Combining Public Human Activity Recognition Datasets to Mitigate Labeled Data Scarcity

The use of supervised learning for Human Activity Recognition (HAR) on m...

Please sign up or login with your details

Forgot password? Click here to reset