Residual-Recursion Autoencoder for Shape Illustration Images
This addresses feature extraction for industrial product cross-sections, but it is incremental as it builds on existing autoencoder methods.
The paper tackles the problem of extracting low-dimensional features from shape illustration images (SIIs) while maintaining high reconstruction accuracy, proposing a Residual-Recursion Autoencoder (RRAE) that recursively fills residuals to improve performance. The result shows reconstruction loss decreased by 86.47% for convolutional autoencoder on SIIs and 8-10% for variational autoencoders on MNIST.
Shape illustration images (SIIs) are common and important in describing the cross-sections of industrial products. Same as MNIST, the handwritten digit images, SIIs are gray or binary and containing shapes that are surrounded by large areas of blanks. In this work, Residual-Recursion Autoencoder (RRAE) has been proposed to extract low-dimensional features from SIIs while maintaining reconstruction accuracy as high as possible. RRAE will try to reconstruct the original image several times and recursively fill the latest residual image to the reserved channel of the encoder's input before the next trial of reconstruction. As a kind of neural network training framework, RRAE can wrap over other autoencoders and increase their performance. From experiment results, the reconstruction loss is decreased by 86.47% for convolutional autoencoder with high-resolution SIIs, 10.77% for variational autoencoder and 8.06% for conditional variational autoencoder with MNIST.