Convolutional Low-Resolution Fine-Grained Classification. In arXiv, 2017.03

Convolutional Low-Resolution Fine-Grained Classification. In arXiv, 2017.03


论文链接:Convolutional Low-Resolution Fine-Grained Classification.

论文的idea很简单,就是把super resolution和classifier嵌入到一个模型中,并end2end训练。

Convolutional Low-Resolution Fine-Grained Classification. In arXiv, 2017.03_第1张图片

至于super resolution,论文作者参考了accurate image super-resolution using very deep convolutional networks. in cvpr16.

Convolutional Low-Resolution Fine-Grained Classification. In arXiv, 2017.03_第2张图片

这篇论文也很简单,但是idea却不简单。

对于想快速入门SR的,推荐看这篇博文:

深度学习在图像超分辨率重建中的应用: https://zhuanlan.zhihu.com/p/25532538

=====
如果这篇博文对你有帮助,可否赏笔者喝杯奶茶?


你可能感兴趣的:(Deep,Learning)