[深度学习论文笔记][Image Classification] Going Deeper with Convolutions

最新推荐文章于 2024-04-23 12:57:33 发布

原创

最新推荐文章于 2024-04-23 12:57:33 发布 · 1.1k 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#Papers #Image Classification #Computer Vision #Deep Learning #CNN

本文是关于深度学习论文的研究笔记，主要探讨了如何通过使用GoogLeNet（Inception网络）在保持计算预算不变的情况下，增加网络的深度和宽度以提高图像分类性能。通过1x1卷积层实现维度调整和增强网络表示能力，减少计算瓶颈。文中详细介绍了网络架构，包括多个Inception模块和辅助分类器的设计，以及训练和数据准备的策略。在ILSVRC-2014比赛中，该模型在top-5错误率上取得了显著成果。

Szegedy, Christian, et al. “Going deeper with convolutions.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015. [Citations: 1576].

1 Motivations

[Increasing Both the Depth and Width of the Network]

• Large number of parameters, more prone to overfitting.

• Increased use of computational resources.

[Motivation] Improve the utility of the computation resources inside the network, then we can increase the depth and width of the network while keeping the computational budget constant.

[Idea] Use 1 × 1 conv layer to

• Increase the representational power of neural networks.
• Dimension reduction to remove computational bottlenecks.

2 Architecture
In a Nutshell (5M Parameters)
• Input (3 × 224 × 224).
• conv1 (64@7 × 7, s2, p3), relu1, pool1 (3 × 3, s2), lrn1, output (64 × 56 × 56).
• conv2-1 (64@1 × 1, s1), rel