Abstract
With large-scale human-annotated pixel-level annotations, many deep learning-based methods have achieved impressive innovations in the field of semantic image segmentation. However, the lack of publicly available Chinese landscape paintings with pixel-level annotations seriously hinders the process of segmentation of Chinese landscape paintings. In addition, a prominent feature of Chinese landscape paintings is the extensive use of black ink, resulting in a lack of color-related information, and landscape paintings often use blank space to depict sky and water elements, which can lead to confusion about boundary information. These issues make the semantic segmentation of Chinese landscape paintings more challenging. To address these challenges, we construct a Segmented Chinese Landscape Paintings (SegCLP) dataset, which contains 709 images with pixel-level annotations belonging to 6 foreground object classes. Moreover, we propose a novel approach called Decrease Dilation Rate Residual Attention Network (DRANet) to enable accurate semantic segmentation of Chinese landscape paintings. DRANet integrates two primary modules: an attention mechanism and a residual module. The attention module alleviates the training burden associated with the spatial convolution pool pyramid, while the residual block enhances the granularity of the decoder, particularly at the segmentation boundary. Experimental findings corroborate the superior efficacy of DRANet in accurately segmenting Chinese landscape images.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.