ParticleAugment: Sampling-based data augmentation
Tsaregorodtsev A, Belagiannis V (2023)
Publication Type: Journal article
Publication year: 2023
Journal
Book Volume: 228
Article Number: 103633
DOI: 10.1016/j.cviu.2023.103633
Abstract
We present an automated data augmentation approach for image classification. The problem is formulated as a Monte Carlo sampling problem where the goal is to approximate the optimal augmentation policies using a policy mixture distribution. We propose a particle filter scheme for the policy search where the probability of applying a set of augmentation operations forms the state of the filter. The policy performance is measured based on the loss function difference between a reference model and the actual model. This performance measure is then used to re-weight the particles and finally update the policy distribution. In our experiments, we show that our formulation for automated augmentation reaches promising results on CIFAR-10, CIFAR-100, and ImageNet datasets using the standard network architectures for this problem. By comparing with the related work, our method reaches a balance between the computational cost of policy search and the model performance. The source code of our approach is publicly available.
Authors with CRIS profile
Involved external institutions
Germany (DE)How to cite
APA:
Tsaregorodtsev, A., & Belagiannis, V. (2023). ParticleAugment: Sampling-based data augmentation. Computer Vision and Image Understanding, 228. https://dx.doi.org/10.1016/j.cviu.2023.103633
MLA:
Tsaregorodtsev, Alexander, and Vasileios Belagiannis. "ParticleAugment: Sampling-based data augmentation." Computer Vision and Image Understanding 228 (2023).
BibTeX: Download