Generative ScatterNet Hybrid Deep Learning (G-SHDL) Network with Structural Priors for Semantic Image Segmentation
This addresses the problem of efficient and accurate image segmentation for computer vision applications, with incremental improvements in training efficiency and performance.
The paper tackles semantic image segmentation by proposing a generative ScatterNet hybrid deep learning network that trains rapidly from small labeled datasets using structural priors, achieving state-of-the-art performance on two image datasets.
This paper proposes a generative ScatterNet hybrid deep learning (G-SHDL) network for semantic image segmentation. The proposed generative architecture is able to train rapidly from relatively small labeled datasets using the introduced structural priors. In addition, the number of filters in each layer of the architecture is optimized resulting in a computationally efficient architecture. The G-SHDL network produces state-of-the-art classification performance against unsupervised and semi-supervised learning on two image datasets. Advantages of the G-SHDL network over supervised methods are demonstrated with experiments performed on training datasets of reduced size.