Dictionary-enabled efficient training of ConvNets for image classification

Usman Haider, Muhammad Hanif, Ahmar Rashid, Syed Fawad Hussain

Abstract: Highlights•ConvNets are powerful for images but computationally expensive.•Paper proposes dictionary-based training for ConvNets exploiting sparsity.•The proposed method preserves orthogonal features and reduces training time.•Results: 4.5x reduction in computational burden.•High accuracy: 97.21% MNIST, 96.81% USPS, 88.4% FASHION.