arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.14729cs.CV
收藏

Targeted Gradient Descent:一种新的卷积神经网络微调和在线学习方法

Targeted Gradient Descent: A Novel Method for Convolutional Neural Networks Fine-tuning and Online-learning

Johns Hopkins University(约翰斯·霍普金斯大学);Canon Medical Research USA, INC.(佳能医疗研究美国公司)

Junyu Chen, Evren Asma, Chung Chan

摘要:

卷积神经网络(ConvNet)通常使用从相同分布中提取的图像进行训练和测试。将ConvNet推广到各种任务通常需要一个完整的训练数据集,该数据集由从不同任务中绘制的图像组成。在大多数情况下,几乎不可能先验地收集每个可能的代表性数据集。只有在ConvNet在临床实践中部署后,新数据才可用。然而,ConvNet可能会在分布外测试样本上生成工件。在这项研究中,我们提出了目标梯度下降(TGD),这是一种新的微调方法,可以将预训练的网络扩展到新任务,而无需重新访问先前任务的数据,同时保留从先前训练中获得的知识。在更进一步的程度上,所提出的方法还使得能够对患者特异性数据进行在线学习。该方法基于重用预训练ConvNet的冗余内核来学习新知识的思想。我们比较了TGD的性能,几种常用的训练方法的正电子发射断层扫描(PET)图像去噪的任务。来自临床图像的结果表明,TGD生成的结果与从头开始的训练相当,同时显着减少了数据准备和网络训练时间。更重要的是,它使在线学习的测试研究,以提高网络的泛化能力,在现实世界中的应用。

英文摘要:

A convolutional neural network (ConvNet) is usually trained and then tested using images drawn from the same distribution. To generalize a ConvNet to various tasks often requires a complete training dataset that consists of images drawn from different tasks. In most scenarios, it is nearly impossible to collect every possible representative dataset as a priori. The new data may only become available after the ConvNet is deployed in clinical practice. ConvNet, however, may generate artifacts on out-of-distribution testing samples. In this study, we present Targeted Gradient Descent (TGD), a novel fine-tuning method that can extend a pre-trained network to a new task without revisiting data from the previous task while preserving the knowledge acquired from previous training. To a further extent, the proposed method also enables online learning of patient-specific data. The method is built on the idea of reusing a pre-trained ConvNet's redundant kernels to learn new knowledge. We compare the performance of TGD to several commonly used training approaches on the task of Positron emission tomography (PET) image denoising. Results from clinical images show that TGD generated results on par with training-from-scratch while significantly reducing data preparation and network training time. More importantly, it enables online learning on the testing study to enhance the network's generalization capability in real-world applications.

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。

↑