专栏名称: 机器学习研究会

机器学习研究会是北京大学大数据与机器学习创新中心旗下的学生组织，旨在构建一个机器学习从事者交流的平台。除了及时分享领域资讯外，协会还会举办各种业界巨头/学术神牛讲座、学术大牛沙龙分享会、real data 创新竞赛等活动。

【学习】CNN图像分割简史：从R-CNN到Mask R-CNN

机器学习研究会 · 公众号 · AI · 2017-04-23 22:03

正文

点击上方 “机器学习研究会” 可以订阅哦

摘要

转自：爱可可-爱生活

At Athelas, we use Convolutional Neural Networks(CNNs) for a lot more than just classification! In this post, we’ll see how CNNs can be used, with great results, in image instance segmentation.

Ever since Alex Krizhevsky, Geoff Hinton, and Ilya Sutskever won ImageNet in 2012, Convolutional Neural Networks(CNNs) have become the gold standard for image classification. In fact, since then, CNNs have improved to the point where they now outperform humans on the ImageNet challenge!

CNNs now outperform humans on the ImageNet challenge. The y-axis in the above graph is the error rate on ImageNet.

While these results are impressive, image classification is far simpler than the complexity and diversity of true human visual understanding.

In classification, there’s generally an image with a single object as the focus and the task is to say what that image is (see above). But when we look at the world around us, we carry out far more complex tasks.