This model is a convolutional neural network for 2D image segmentation tuned to avoid overfitting.
This UNet model is adapted from the original version of the UNet model which is a convolutional auto-encoder for 2D image segmentation. UNet was first introduced by Olaf Ronneberger, Philip Fischer, and Thomas Brox in the paper: UNet: Convolutional Networks for Biomedical Image Segmentation.
This work proposes a modified version of UNet, called
TinyUNet which performs efficiently and with very high accuracy
on the industrial anomaly dataset DAGM2007.
TinyUNet, like the original UNet is composed of two parts:
It repeatedly applies 3 downsampling blocks composed of two 2D convolutions followed by a 2D max pooling layer in the encoding sub-network. In the decoding sub-network, 3 upsampling blocks are composed of a upsample2D layer followed by a 2D convolution, a concatenation operation with the residual connection and two 2D convolutions.
TinyUNet has been introduced to reduce the model capacity which was leading to a high degree of over-fitting on a
small dataset like DAGM2007. The complete architecture is presented in the figure below:
Figure 1. Architecture of the UNet Industrial
The following datasets were used to train this model:
Performance numbers for this model are available in NGC