Affiliation:
1. Loc Nguyen's Academic Network
Abstract
Abstract
Deconvolution task is not important in convolutional neural network (CNN) because it is not imperative to recover convoluted image when convolutional layer is important to extract features. However, the deconvolution task is useful in some cases of inspecting and reflecting a convolutional filter as well as trying to improve a generated image when information loss is not serious with regard to trade-off of information loss and specific features such as edge detection and sharpening. This research proposes a duplicated and reverse process of recovering a filtered image. Firstly, source layer and target layer are reversed in accordance with traditional image convolution so as to train the convolutional filter. Secondly, the trained filter is reversed again to derive a deconvolutional operator for recovering the filtered image. The reverse process is associated with backpropagation algorithm which is most popular in learning neural network. Experimental results show that the proposed technique in this research is better to learn the filters that focus on discovering pixel differences. Therefore, the main contribution of this research is to inspect convolutional filters from data.
Publisher
Research Square Platform LLC
Reference4 articles.
1. Cao, F., Yao, K., & Liang, J. (2020, September 23). Deconvolutional neural network for image super-resolution. Neural Networks, 132, 394–404. doi:10.1016/j.neunet.2020.09.017
2. January 22). Single-Image Super-resolution Using Sparse Regression and Natural Image Prior;Kim K;IEEE Transactions on Pattern Analysis and Machine Intelligence,2010
3. January 18). A Deep Convolutional Auto-Encoder with Pooling - Unpooling Layers in Caffe;Turchenko V;arXiv preprint,2017
4. Xu, L., Ren, J. S., Liu, C., & Jia, J. (2014). Deep Convolutional Neural Network for Image Deconvolution. Deep Convolutional Neural Network for Image (NIPS 2014). 27. NeurIPS. Retrieved from https://proceedings.neurips.cc/paper_files/paper/2014/hash/1c1d4df596d01da60385f0bb17a4a9e0-Abstract.html