andy
7bc4dffd8b
Affected files: STEM/AI/Neural Networks/CNN/Examples.md STEM/AI/Neural Networks/CNN/FCN/FCN.md STEM/AI/Neural Networks/CNN/FCN/ResNet.md STEM/AI/Neural Networks/CNN/FCN/Skip Connections.md STEM/AI/Neural Networks/CNN/GAN/DC-GAN.md STEM/AI/Neural Networks/CNN/GAN/GAN.md STEM/AI/Neural Networks/CNN/Interpretation.md STEM/AI/Neural Networks/CNN/UpConv.md STEM/AI/Neural Networks/Deep Learning.md STEM/AI/Neural Networks/MLP/MLP.md STEM/AI/Neural Networks/Properties+Capabilities.md STEM/AI/Neural Networks/SLP/Least Mean Square.md STEM/AI/Neural Networks/SLP/SLP.md STEM/AI/Neural Networks/Transformers/Transformers.md STEM/AI/Properties.md STEM/CS/Language Binding.md STEM/CS/Languages/dotNet.md STEM/Signal Proc/Image/Image Processing.md
41 lines
1.2 KiB
Markdown
41 lines
1.2 KiB
Markdown
Fully [Convolution](../../../../Signal%20Proc/Convolution.md)al Network
|
|
|
|
[Convolutional](../Convolutional%20Layer.md) and [up-convolutional layers](../UpConv.md) with [ReLu](../../Activation%20Functions.md#ReLu) but no others (pooling)
|
|
- All some sort of Encoder-Decoder
|
|
|
|
Contractive → [UpConv](../UpConv.md)
|
|
|
|
# Image Segmentation
|
|
- For visual output
|
|
- Previously image $\rightarrow$ vector
|
|
- Additional layers to up-sample representation to an image
|
|
- Up-[convolution](../../../../Signal%20Proc/Convolution.md)al
|
|
- De-[convolution](../../../../Signal%20Proc/Convolution.md)al
|
|
|
|
|
|
|
|
|
|
# Training
|
|
- Rarely from scratch
|
|
- Pre-trained weights
|
|
- Replace final layers
|
|
- [FC](../../MLP/MLP.md) layers
|
|
- White-noise initialised
|
|
- Add [UpConv](../UpConv.md) layer(s)
|
|
- Fine-tune train
|
|
- Freeze others
|
|
- Annotated GT images
|
|
- Can use summed per-pixel log [loss](../../Deep%20Learning.md#Loss%20Function)
|
|
|
|
# Evaluation
|
|
|
|
- SDS
|
|
- Classical method
|
|
- 52% mAP
|
|
- FCN
|
|
- 62% mAP
|
|
- Intersection over Union
|
|
- IOU
|
|
- Jaccard
|
|
- Averaged over all images
|
|
- $J(A,B)=\frac{|A\cap B|}{|A\cup B|}$ |