arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2007.07423cs.CVcs.LG
收藏

比较学习:通过比较图像表示超越X光片上的ImageNet预训练

Comparing to Learn: Surpassing ImageNet Pretraining on Radiographs By Comparing Image Representations

Jarvis Lab, Tencent(腾讯 Jarvis Lab)

Hong-Yu Zhou, Shuang Yu, Cheng Bian, Yifan Hu, Kai Ma, Yefeng Zheng

摘要:

在深度学习时代,预训练模型在医学图像分析中发挥着重要作用,其中ImageNet预训练被广泛采用。然而,不可否认的是,自然图像和医学图像之间存在着明显的领域鸿沟。为了弥补这一差距,我们提出了一种新的预训练方法,该方法在没有手动注释的情况下从70万张射线照片中学习。我们称我们的方法为比较学习(C2L),因为它通过比较不同的图像表示来学习鲁棒的特征。为了验证C2L的有效性,我们进行了全面的消融研究,并在不同的任务和数据集上进行了评估。在X射线照片上的实验结果表明,C2L可以显著优于ImageNet预训练和以前的最先进方法。代码和模型可用。

英文摘要:

In deep learning era, pretrained models play an important role in medical image analysis, in which ImageNet pretraining has been widely adopted as the best way. However, it is undeniable that there exists an obvious domain gap between natural images and medical images. To bridge this gap, we propose a new pretraining method which learns from 700k radiographs given no manual annotations. We call our method as Comparing to Learn (C2L) because it learns robust features by comparing different image representations. To verify the effectiveness of C2L, we conduct comprehensive ablation studies and evaluate it on different tasks and datasets. The experimental results on radiographs show that C2L can outperform ImageNet pretraining and previous state-of-the-art approaches significantly. Code and models are available.

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。

↑