Multiexpert Adversarial Regularization for Robust and Data-Efficient Deep Supervised Learning

Multiexpert Adversarial Regularization for Robust and Data-Efficient Deep Supervised Learning

Deep neural networks (DNNs) can achieve high accuracy when there is abundant training data that has the same distribution as the test data. In practical applications, data deficiency is often a concern. For classification tasks, the lack of enough labeled images in the training set often results in...

Full description

Bibliographic Details
Main Authors: Behnam Gholami, Qingfeng Liu, Mostafa El-Khamy, Jungwon Lee
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Image classification
image segmentation
data efficient learning
robust learning
ensemble methods
adversarial learning
Online Access:https://ieeexplore.ieee.org/document/9853519/

Internet

https://ieeexplore.ieee.org/document/9853519/

Similar Items