SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

[guanfuchen]

use the code for training CamVid, here is the sample result

when the arch segnet-vgg16 change to segnet-vgg19, the detail about pedestrian is more clear.

[guanfuchen]

Training Skills:

• We perform local contrast normalization [54] to the RGB input.
• We use median frequency balancing [14] where the weight assigned to a class in the loss function is the ratio of the median of class frequencies computed on the entire training set divided by the class frequency.

** local contrast normalization

• 参考资料local contrast normalization和[feature request] Add Local Contrast Normalization