Volume 14, Number 2

EDGE-Net: Efficient Deep-Learning Gradients Extraction Network

  Authors

Nasrin Akbari and Amirali Baniasadi, University of Victoria, Canada

  Abstract

Deep Convolutional Neural Networks (CNNs) have achieved impressive performance in edge detection tasks, but their large number of parameters often leads to high memory and energy costs for implementation on lightweight devices. In this paper, we propose a new architecture, called Efficient Deep-learning Gradients Extraction Network (EDGE-Net), that integrates the advantages of Depthwise Separable Convolutions and deformable convolutional networks (DeformableConvNet) to address these inefficiencies. By carefully selecting proper components and utilizing network pruning techniques, our proposed EDGE-Net achieves state-of-the-art accuracy in edge detection while significantly reducing complexity. Experimental results on BSDS500 and NYUDv2 datasets demonstrate that EDGE-Net outperforms current lightweight edge detectors with only 500k parameters, without relying on pre-trained weights.

  Keywords

Efficient edge detection, lightweight deep neural network, Enhanced receptive field.