LVP-net: A deep network of learning visual pathway for edge detection.

Deep learning-based edge detectors typically consist of the encoder and the decoder. To integrate multi-scale features into a global edge map effectively, researchers utilize classification networks such as VGG16 as the encoder and focus on the decoder architecture. In contrast to existing approaches, we propose a novel deep network for edge detection called learning-visual-pathway network (LVP-Net), in which an enhancer-encoder-decoder architecture is designed inspired by the biological visual pathway: the retina/lateral geniculate nucleus → the primary visual cortex (V1) → V2 → V4 → the inferior temporal cortex (IT). To simulate the visual mechanisms along this pathway, we design a feature enhancer network (FENet) that boosts the feature representation capability of the encoder. FENet is combined with VGG16 based on the hierarchical structure of the pathway. Furthermore, inspired by the integration ability of multiple features in IT, we introduce a feedforward fusion module (FFM). Finally, we evaluate LVP-Net on three benchmark datasets, i.e., BSDS500, NYUDv2, and Multicue. Experimental results demonstrate that our method achieves competitive performance compared with most state-of-the-art approaches. [Display omitted] • This is the first study to employ the color-opponent mechanism in deep learning. • CNN is utilized to mimic visual mechanisms along the visual pathway. • According to the characteristics of the visual pathway, we construct an enhancer-encoder-decoder architecture. • The evaluation shows our method obtains a quite competitive performance on different datasets. [ABSTRACT FROM AUTHOR]