Stacking-based Deep Neural Network: Deep Analytic Network on Convolutional Spectral Histogram Features
This work addresses object recognition tasks in domains such as faces, digits, and natural objects, but it is incremental as it builds on existing stacking-based deep neural network methods.
The paper tackled object recognition by proposing a deep analytic network (DAN) based on spectral histogram features, achieving performance improvements over the baseline on datasets like FERET, MNIST, and CIFAR10.
Stacking-based deep neural network (S-DNN), in general, denotes a deep neural network (DNN) resemblance in terms of its very deep, feedforward network architecture. The typical S-DNN aggregates a variable number of individually learnable modules in series to assemble a DNN-alike alternative to the targeted object recognition tasks. This work likewise devises an S-DNN instantiation, dubbed deep analytic network (DAN), on top of the spectral histogram (SH) features. The DAN learning principle relies on ridge regression, and some key DNN constituents, specifically, rectified linear unit, fine-tuning, and normalization. The DAN aptitude is scrutinized on three repositories of varying domains, including FERET (faces), MNIST (handwritten digits), and CIFAR10 (natural objects). The empirical results unveil that DAN escalates the SH baseline performance over a sufficiently deep layer.