LDC: Lightweight Dense CNN for Edge Detection
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.
PDF AbstractCode
Tasks
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Edge Detection | BIPED | LDC | ODS | 0.889 | # 3 | |
Number of parameters (M) | 674K | # 1 | ||||
Edge Detection | BRIND | LDC | ODS | 0.790 | # 1 | |
Number of parameters (M) | 674K | # 1 | ||||
Edge Detection | MDBD | LDC | ODS | 0.880 | # 5 | |
Number of parameters (M) | 674K | # 1 | ||||
Edge Detection | UDED | LDC | ODS | 0.817 | # 2 |