CSC-Unet: A Novel Convolutional Sparse Coding Strategy Based Neural Network for Semantic Segmentation

arXiv:2108.00408v2 Announce Type: replace-cross
Abstract: It is a challenging task to accurately perform semantic segmentation due to the complexity of real picture scenes. Many semantic segmentation methods based on traditional deep learning insufficiently captured the semantic and appearance information of images, which put limit on their generality and robustness for various application scenes. In this paper, we proposed a novel strategy that reformulated the popularly-used convolution operation to multi-layer convolutional sparse coding block to ease the aforementioned deficiency. This strategy …

abstract arxiv coding complexity cs.ai cs.cv cs.lg deep learning images information network neural network novel segmentation semantic strategy type unet