发帖
雷达卡
Saccader: Improving Accuracy of Hard Attention
Models for Vision
Gamaleldin F. Elsayed Simon Kornblith Quoc V. Le
Google Research, Brain Team Google Research, Brain Team Google Research, Brain Team
gamaleldin@google.com
Abstract
Although deep convolutional neural networks achieve state-of-the-art performance
across nearly all image classification tasks, their decisions are difficult to interpret.
One approach that ...
京公网安备 11010802022788号
