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 2105.03056cs.CV
收藏

常见植物图像分类的少样本学习

Few-Shot Learning for Image Classification of Common Flora

Edward E. Whitacre Jr. College of Engineering(爱德华·E·惠特克二世工程学院)

Joshua Ball

摘要:

在Few-Shot图像分类任务中使用元学习和迁移学习是一个很好的研究领域,许多论文展示了在数据丰富并且对计算资源没有重大限制的情况下,迁移学习相对于元学习的优势。在本文中,我们将展示我们的实验结果,测试各种最先进的迁移学习权重和架构,以及利用模型不可知Meta Learning(MAML)进行图像分类的元学习领域中类似的最先进作品。我们的研究结果表明,当数据集足够大时,这两种做法都提供了足够的性能,但当引入数据稀疏性以保持足够的性能时,它们也会很难。通过使用图像增强和超参数的微调,这个问题得到了适度的缓解。在本文中,我们将讨论:(1)我们为Few-Shot图像分类任务开发一个强大的多类卷积神经网络(CNN)的过程,(2)证明迁移学习是帮助创建图像分类模型的最佳方法,当数据集很大时,(3)在数据非常有限的情况下,MAML优于迁移学习。代码可以在这里找到:github.com/JBall1/Few-Shot-Limited-Data

英文摘要:

The use of meta-learning and transfer learning in the task of few-shot image classification is a well researched area with many papers showcasing the advantages of transfer learning over meta-learning in cases where data is plentiful and there is no major limitations to computational resources. In this paper we will showcase our experimental results from testing various state-of-the-art transfer learning weights and architectures versus similar state-of-the-art works in the meta-learning field for image classification utilizing Model-Agnostic Meta Learning (MAML). Our results show that both practices provide adequate performance when the dataset is sufficiently large, but that they both also struggle when data sparsity is introduced to maintain sufficient performance. This problem is moderately reduced with the use of image augmentation and the fine-tuning of hyperparameters. In this paper we will discuss: (1) our process of developing a robust multi-class convolutional neural network (CNN) for the task of few-shot image classification, (2) demonstrate that transfer learning is the superior method of helping create an image classification model when the dataset is large and (3) that MAML outperforms transfer learning in the case where data is very limited. The code is available here: github.com/JBall1/Few-Shot-Limited-Data

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。

↑