ScatterNet Hybrid Deep Learning (SHDL) Network For Object Classification
This work addresses object recognition for computer vision applications, but appears incremental as it builds on existing deep learning and ScatterNet concepts.
The paper tackled object classification by proposing the ScatterNet Hybrid Deep Learning (SHDL) network, which extracts invariant and discriminative image representations and achieves state-of-the-art performance against unsupervised and semi-supervised methods on two image datasets.
The paper proposes the ScatterNet Hybrid Deep Learning (SHDL) network that extracts invariant and discriminative image representations for object recognition. SHDL framework is constructed with a multi-layer ScatterNet front-end, an unsupervised learning middle, and a supervised learning back-end module. Each layer of the SHDL network is automatically designed as an explicit optimization problem leading to an optimal deep learning architecture with improved computational performance as compared to the more usual deep network architectures. SHDL network produces the state-of-the-art classification performance against unsupervised and semi-supervised learning (GANs) on two image datasets. Advantages of the SHDL network over supervised methods (NIN, VGG) are also demonstrated with experiments performed on training datasets of reduced size.