Local Patch AutoAugment with Multi-Agent Collaboration

TL;DR

This paper introduces Patch AutoAugment, a fine-grained data augmentation method using multi-agent reinforcement learning to optimize local patch policies, improving model generalization with less computation.

Contribution

It proposes a novel multi-agent reinforcement learning framework for patch-level data augmentation, enhancing diversity and effectiveness over image-level methods.

Findings

Outperforms state-of-the-art DA methods on multiple datasets

Requires fewer computational resources

Improves generalization in image classification tasks

Abstract

Data augmentation (DA) plays a critical role in improving the generalization of deep learning models. Recent works on automatically searching for DA policies from data have achieved great success. However, existing automated DA methods generally perform the search at the image level, which limits the exploration of diversity in local regions. In this paper, we propose a more fine-grained automated DA approach, dubbed Patch AutoAugment, to divide an image into a grid of patches and search for the joint optimal augmentation policies for the patches. We formulate it as a multi-agent reinforcement learning (MARL) problem, where each agent learns an augmentation policy for each patch based on its content together with the semantics of the whole image. The agents cooperate with each other to achieve the optimal augmentation effect of the entire image by sharing a team reward. We show the effectiveness of our method on multiple benchmark datasets of image classification and fine-grained image recognition (e.g., CIFAR-10, CIFAR-100, ImageNet, CUB-200-2011, Stanford Cars and FGVC-Aircraft). Extensive experiments demonstrate that our method outperforms the state-of-the-art DA methods while requiring fewer computational resources.