[深度学习论文笔记][Image Classification] Very Deep Convolutional Networks for Large-Scale Image Recognitio

Hao_Zhang_Vision

于 2016-09-25 16:07:15 发布

阅读量848

点赞数

分类专栏： CNN Papers 文章标签： Computer Vision CNN Deep Learning Papers Image Classification

本文链接：https://blog.youkuaiyun.com/Hao_Zhang_Vision/article/details/52662607

版权

本文笔记探讨了深度学习中非常深的卷积网络在大规模图像识别任务中的应用。介绍了网络架构、数据增强策略，如水平翻转图像，并讨论了训练细节。实验结果显示，多尺度评估优于固定尺度策略，而局部响应归一化（LRN）并未提高准确性。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Simonyan, Karen, and Andrew Zisserman. “Very deep convolutional networks for large-scale image recognition.” arXiv preprint arXiv:1409.1556 (2014). [Citations: 1986].

1 Motivation

[Ways to Improve Accuracy]
• Use small fliter size and small stride in the first conv layer.
• Training and testing the network densely over the whole image and over multiple scales.
• Depth of the network.

2 Architecture

[In a Nutshell (138M Parameters)]
• Input (3 × 224 × 224).
• conv1-1 (64@3 × 3, s1, p1), relu1-1.
• conv1-2 (64@3 × 3, s1, p1), relu1-2.
• pool1 (2 × 2, s2), output 64 × 112 × 112.
• conv2-1 (128@3 × 3, s1, p1), relu2-1.
• conv2-2 (128@3 × 3, s1, p1), relu2-2.
• pool2 (2 × 2, s2), output 128 × 56 × 56.
• conv3-1 (256@3 × 3, s1, p1), relu3-1.
• conv3-2 (256@3 × 3, s1, p1), relu3-2.
• conv3-3 (256@3 ×

最低0.47元/天解锁文章