具有多智能体协作的本地补丁AutoAugment
Local Patch AutoAugment with Multi-Agent Collaboration
摘要：
数据增强（DA）在提高深度学习模型的泛化能力方面起着至关重要的作用。最近的作品自动搜索DA政策的数据已经取得了巨大的成功。然而，现有的自动DA方法通常在图像级执行搜索，这限制了局部区域多样性的探索。在本文中，我们提出了一个更细粒度的自动DA方法，被称为补丁AutoAugment，划分成一个网格的补丁图像和搜索的联合最佳增强策略的补丁。我们制定它作为一个多智能体强化学习（MARL）的问题，其中每个代理学习的增强策略，每个补丁的基础上，其内容连同整个图像的语义。智能体相互合作，通过分享团队奖励来实现整个图像的最佳增强效果。我们展示了我们的方法在多个图像分类和细粒度图像识别的基准数据集上的有效性（例如，CIFAR-10、CIFAR-100、ImageNet、CUB-200-2011、Stanford Cars和FGVC-Aircraft）。大量的实验表明，我们的方法优于国家的最先进的DA方法，同时需要更少的计算资源。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
