%0 Journal Article
%T LDC: Lightweight Dense CNN for Edge Detection
%A Xavier Soria
%A Gonzalo Pomboza-Junez
%A Angel Sappa
%J IEEE Access
%D 2022
%V 10
%I IEEE
%F Xavier Soria2022
%O MSIAU; MACO; 600.160; 600.167
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3751), last updated on Tue, 25 Apr 2023 15:36:46 +0200
%X This paper presents a Lightweight Dense Convolutional (LDC) neural network for edge detection. The proposed model is an adaptation of two state-of-the-art approaches, but it requires less than 4% of parameters in comparison with these approaches. The proposed architecture generates thin edge maps and reaches the highest score (i.e., ODS) when compared with lightweight models (models with less than 1 million parameters), and reaches a similar performance when compare with heavy architectures (models with about 35 million parameters). Both quantitative and qualitative results and comparisons with state-of-the-art models, using different edge detection datasets, are provided. The proposed LDC does not use pre-trained weights and requires straightforward hyper-parameter settings. The source code is released at https://github.com/xavysp/LDC
%U http://dx.doi.org/10.1109/ACCESS.2022.3186344
%P 68281-68290