[深度学习论文笔记][Image Classification] 图像分类部分论文导读

最新推荐文章于 2020-08-04 15:18:24 发布

Hao_Zhang_Vision

最新推荐文章于 2020-08-04 15:18:24 发布

阅读量2.4k

点赞数

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

本文链接：https://blog.csdn.net/Hao_Zhang_Vision/article/details/52784680

版权

本文汇集了网络上的图像分类论文资源，并通过Amazon Mechanical Turk进行标注。研究涉及多种架构，如Dropout、GoogLeNet、VGGNet和ResNet，同时提到了Xavier初始化方法的应用。

摘要由CSDN通过智能技术生成

[ImageNet]
• Over 15M labeled high resolution images.
• Roughly 22k categories.

• Collected from web and labeled by Amazon Mechanical Turk.

[ILSVRC (ImageNet Large-Scale Visual Recognition Challenge)]
• Annual competition of image classification at large scale.
• 1.2M training images, 50k validation images, and 150k testing images.
• 1k categories.
• Resolution of each image varies.
• Classification: make 5 guesses about the image label (top-5 error).

[Architectures] See Tab. 1.

AlexNet
• Deeper, bigger than LeNet.
• Featured conv layer stacked on top of each other (previously it was common to only have a single conv layer always immediately followed by a pool layer).
• First use of ReLU.
• Heavy data augmentation.

• Dropout.

ZFNet
• Improvement on AlexNet by tweaking the architecture hyperparamet