Sth about DL: Receptive field(RF, 感受野)

Why it is important

  • RF is the corresponding field in the original input data of a pixel in the feature map of a certain layer.
  • A larger RF means more global features while a smaller one indicates detailed and local features. It can be considered as an indicater of the extent of abstractness.
  • It affects where and how big are the convs within the network are 'seeing' in the original input.

Calculation

  • RF calculation for CNN, dependent on previous layers

    r is RF, k is kernal size, and s is stride. RF of the input data is 1.

  • RF for dilated conv
    The above equation holds, and the only difference is that the kernal size now needs to be translated into the size for a non-dilated conv. For instance, the kernal size of 3 with a rate of 1 is tranlated into 3; the kernal size of 3 with a rate of 2 is tranlated into 5; the kernal size of 3 with a rate of 4 is tranlated into 9.
    How to translate?
    (rate-1) zeros are inserted between each two pixels of the kernal.

Questions

  • RF is only a small part of the black box, it is more about the size and not about the location: how to better control it to learn better features?
  • Isn't it wierd to have a RF even larger than the input data size in the last layer? Or the point of DL model is redundancy?

Reference for details

©著作权归作者所有,转载或内容合作请联系作者
平台声明:文章内容(如有图片或视频亦包括在内)由作者上传并发布,文章内容仅代表作者本人观点,简书系信息发布平台,仅提供信息存储服务。

推荐阅读更多精彩内容

  • rljs by sennchi Timeline of History Part One The Cognitiv...
    sennchi阅读 7,486评论 0 10
  • The Inner Game of Tennis W Timothy Gallwey Jonathan Cape ...
    网事_79a3阅读 12,390评论 3 20
  • **2014真题Directions:Read the following text. Choose the be...
    又是夜半惊坐起阅读 10,061评论 0 23
  • 再次到了拉背的日子,可是如何能把枯燥的拉背练好,还真是技术活呢。 21天减脂第12天。拉背日。照旧是引体向上正手反...
    嘟嘟白白爸爸阅读 214评论 0 0
  • 看完其实觉得没有在书中那种被牵着鼻子走的感觉 ,对书上人物形象也反映得不够好。怎么说呢,有几个片段也实在很催泪。 ...
    茶祭阅读 139评论 0 0