arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.06975cs.CVcs.LG
收藏

面向分布外泛化的基于视觉的机器学习算法

Vision Based Machine Learning Algorithms for Out-of-Distribution Generalisation

Dublin City University(都柏林城市大学)

Hamza Riaz, Alan F. Smeaton

AI总结:

该研究针对计算机视觉中模型面临分布外数据时性能下降的问题,对比了域特定与域泛化视觉方法,经PACS、Office-Home基准实验验证,简单CNN深度学习方法域泛化能力弱于其他完善方法。

摘要:

在目标分割、分类、目标检测和重建等众多计算机视觉应用中,机器学习(ML)都展现出了当前最优的性能。如今,我们能够为这类应用开发出具备实用精度的机器学习工具。然而,每一种工具都仅在其训练和开发所处的域内表现良好。通常情况下,当我们在某一特定域的数据集上训练模型,再在另一个未见过的域(即分布外(OOD)数据集)上进行测试时,模型或机器学习工具的性能会出现下降。例如,当我们在真实世界图像上训练一个简单的分类器,再将该模型应用于类别相同但域不同的图像(如卡通、绘画或素描)时,机器学习工具的表现会令人失望。这带来了域泛化(DG)、域适应(DA)和域偏移方面的严峻挑战。为了提升机器学习工具的性能,我们可以从头开始重建和重新训练模型,也可以进行迁移学习。在本文中,我们针对基于视觉的技术,开展了域特定方法与域泛化方法之间的对比研究。本研究指出,基于简单卷积神经网络(CNN)的深度学习方法在应对域偏移时表现不佳。我们在两个常用的基于视觉的基准数据集PACS和Office-Home上开展了实验,介绍了一种用于域泛化方法和传统深度学习模型的实现流程。实验结果证实,与其他更完善的方法相比,基于CNN的深度学习模型的泛化能力较差。

英文摘要:

There are many computer vision applications including object segmentation, classification, object detection, and reconstruction for which machine learning (ML) shows state-of-the-art performance. Nowadays, we can build ML tools for such applications with real-world accuracy. However, each tool works well within the domain in which it has been trained and developed. Often, when we train a model on a dataset in one specific domain and test on another unseen domain known as an out of distribution (OOD) dataset, models or ML tools show a decrease in performance. For instance, when we train a simple classifier on real-world images and apply that model on the same classes but with a different domain like cartoons, paintings or sketches then the performance of ML tools disappoints. This presents serious challenges of domain generalisation (DG), domain adaptation (DA), and domain shifting. To enhance the power of ML tools, we can rebuild and retrain models from scratch or we can perform transfer learning. In this paper, we present a comparison study between vision-based technologies for domain-specific and domain-generalised methods. In this research we highlight that simple convolutional neural network (CNN) based deep learning methods perform poorly when they have to tackle domain shifting. Experiments are conducted on two popular vision-based benchmarks, PACS and Office-Home. We introduce an implementation pipeline for domain generalisation methods and conventional deep learning models. The outcome confirms that CNN-based deep learning models show poor generalisation compare to other extensive methods.

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。

↑