Local Patch AutoAugment With Multi-Agent Collaboration

doi:10.1109/TMM.2023.3270635

Local Patch AutoAugment With Multi-Agent Collaboration

2024-01-01

1

OA

AI

DOI：10.1109/TMM.2023.3270635

原文链接

原文求助

摘要

En 中文

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, fine-grained image recognition and object detection (e.g., CIFAR-10, CIFAR-100, ImageNet, CUB-200-2011, Stanford Cars, FGVC-Aircraft and Pascal VOC 2007). Extensive experiments demonstrate that our method outperforms the state-of-the-art DA methods while requiring fewer computational resources.

Keyword:

Automatic augmentation

data augmentation

multi-agent reinforcement learning

reinforcement learning

Local Patch AutoAugment With Multi-Agent Collaboration

摘要

期刊

机构