Semantic segmentation with U-Net - Class review
Last updated on：a year ago
Semantic image segmentation predicts a label for every single pixel in an image with appropriate class labels.
Semantic segmentation: Locating objects in an image by predicting each pixel as to which class it belongs to.
Motivation for U-Net
per-pixel class labels
Output: segmentation map
U-Net uses an equal number of convolutional blocks and transposed convolutions for down-sampling and up-sampling.
Deep learning for semantic segmentation
Output: $h \times w \times n$, where n = number of output classes
Output dimension: $s(n_h - 1) + f_h - 2p \times s(n_w - 1) + f_w - 2p$, where n is input size without channel size, f is kernel size, and then p is padding, s is stride.
Motivation: turn a small input into a bigger output. Ignore padding region, add overlap values together
Skip connections are used to prevent border pixel information loss and overfitting in U-Net. Draw it which looks like a U.
 Deeplearning.ai, Convolutional Neural Networks
本博客所有文章除特别声明外，均采用 CC BY-SA 4.0 协议 ，转载请注明出处！