感受野、下采样相关

关于感受野：

• “One of the basic concepts in deep CNNs is the receptive field, or field of view, of a unit in a certain layer in the network. Unlike in fully connected networks, where the value of each unit depends on the entire input to the network, a unit in convolutional networks only depends on a region of the input. This region in the input is the receptive field for that unit
  The concept of receptive field is important for understanding and diagnosing how deep CNNs work. Since anywhere in an input image outside the receptive field of a unit does not affect the value of that unit, it is necessary to carefully control the receptive field, to ensure that it covers the entire relevant image region. In many tasks, especially dense prediction tasks like semantic image segmentation, stereo and optical flow estimation, where we make a prediction for each single pixel in the input image, it is critical for each output pixel to have a big receptive field, such that no important information is left out when making the prediction. The receptive field size of a unit can be increased in a number of ways. One option is to stack more layers to make the network deeper, which increases the receptive field size linearly by theory, as each extra layer increases the receptive field size by the kernel size. Sub-sampling on the other hand increases the receptive field size multiplicatively” [1]
• 我个人的理解，如果feature map的感受野大，那么它作为特征，就有较大的代表性。
• 增大感受野的方式：
  • 卷积，和层数成线性关系，stride=1, (kernel_size-1)*layer + 1
  • 下采样，但丢失了信息；
  • 空洞卷积，不丢失信息。
• 感受野的计算：
  https://zhuanlan.zhihu.com/p/31004121

下采样

• Getting rid of pooling. Many people dislike the pooling operation and think that we can get away without it. For example, Striving for Simplicity: The All Convolutional Net proposes to discard the pooling layer in favor of architecture that only consists of repeated CONV layers. To reduce the size of the representation they suggest using larger stride in CONV layer once in a while. Discarding pooling layers has also been found to be important in training good generative models, such as variational autoencoders (VAEs) or generative adversarial networks (GANs). It seems likely that future architectures will feature very few to no pooling layers. (–cs231n)

pytorch 中 尺寸的计算（下采和卷积相同）

---

• 参考文献：
  【1】Understanding the Effective Receptive Field in Deep Convolutional Neural Networks，Wenjie Luo, Yujia Li, Raquel Urtasun, Richard Zemel。