DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification

08/29/2018
by   Xiaofeng Zhang, et al.
0

Deep learning has revolutionized the performance of classification, but meanwhile demands sufficient labeled data for training. Given insufficient data, while many techniques have been developed to help combat overfitting, the challenge remains if one tries to train deep networks, especially in the ill-posed extremely low data regimes: only a small set of labeled data are available, and nothing -- including unlabeled data -- else. Such regimes arise from practical situations where not only data labeling but also data collection itself is expensive. We propose a deep adversarial data augmentation (DADA) technique to address the problem, in which we elaborately formulate data augmentation as a problem of training a class-conditional and supervised generative adversarial network (GAN). Specifically, a new discriminator loss is proposed to fit the goal of data augmentation, through which both real and augmented samples are enforced to contribute to and be consistent in finding the decision boundaries. Tailored training techniques are developed accordingly. To quantitatively validate its effectiveness, we first perform extensive simulations to show that DADA substantially outperforms both traditional data augmentation and a few GAN-based options. We then extend experiments to three real-world small labeled datasets where existing data augmentation and/or transfer learning strategies are either less effective or infeasible. All results endorse the superior capability of DADA in enhancing the generalization ability of deep networks trained in practical extremely low data regimes. Source code is available at https://github.com/SchafferZhang/DADA.

READ FULL TEXT

page 13

page 14

research
03/27/2023

Data Augmentation for Environmental Sound Classification Using Diffusion Probabilistic Model with Top-k Selection Discriminator

Despite consistent advancement in powerful deep learning techniques in r...
research
11/18/2020

DeepNAG: Deep Non-Adversarial Gesture Generation

Synthetic data generation to improve classification performance (data au...
research
05/26/2018

Transductive Label Augmentation for Improved Deep Network Learning

A major impediment to the application of deep learning to real-world pro...
research
05/27/2023

Toward Understanding Generative Data Augmentation

Generative data augmentation, which scales datasets by obtaining fake la...
research
07/16/2022

Progress and limitations of deep networks to recognize objects in unusual poses

Deep networks should be robust to rare events if they are to be successf...
research
06/13/2019

CoopSubNet: Cooperating Subnetwork for Data-Driven Regularization of Deep Networks under Limited Training Budgets

Deep networks are an integral part of the current machine learning parad...
research
03/30/2020

Adversarial Feature Hallucination Networks for Few-Shot Learning

The recent flourish of deep learning in various tasks is largely accredi...

Please sign up or login with your details

Forgot password? Click here to reset