We propose a novel architecture based on the strucuture of AutoEncoders. The paper introduces CrossEncoders - an AutoEncoder architecture which uses cross-connections to connect layers (both adjacent and non-adjacent) in the encoder and decoder side of the network respectively. The network incorporates both global and local information in the lower dimension code. We aim for an image compression algorithm that has reduced training time and better generalization property. The use of cross-connections makes the training of our network significantly faster. The performance of the proposed framework has been evaluated using real-world data from highly competitive datasets like MNIST and CIFAR-10. Furthermore, we show that the proposed architecture provides high compression ratio and is robust as compared to previously proposed architectures and PCA. The results were validated using metrics, such as PSNR-HVS and PSNR-HVS-M respectively.
Chirag Agarwal, Mehdi Sharifzadeh, Dan Schonfeld, "CrossEncoders: A complex neural network compression framework" in Proc. IS&T Int’l. Symp. on Electronic Imaging: Visual Information Processing and Communication IX, 2018, pp 153-1 - 153-5, https://doi.org/10.2352/ISSN.2470-1173.2018.2.VIPC-153