Enhancing Deep Edge Detection through Normalized Hadamard-Product Fusion

Autor: Gang Hu, Conner Saeli
Jazyk: angličtina
Rok vydání: 2024
Předmět:
Zdroj: Journal of Imaging, Vol 10, Iss 3, p 62 (2024)
Druh dokumentu: article
ISSN: 2313-433X
DOI: 10.3390/jimaging10030062
Popis: Deep edge detection is challenging, especially with the existing methods, like HED (holistic edge detection). These methods combine multiple feature side outputs (SOs) to create the final edge map, but they neglect diverse edge importance within one output. This creates a problem: to include desired edges, unwanted noise must also be accepted. As a result, the output often has increased noise or thick edges, ignoring important boundaries. To address this, we propose a new approach called the normalized Hadamard-product (NHP) operation-based deep network for edge detection. By multiplying the side outputs from the backbone network, the Hadamard-product operation encourages agreement among features across different scales while suppressing disagreed weak signals. This method produces additional Mutually Agreed Salient Edge (MASE) maps to enrich the hierarchical level of side outputs without adding complexity. Our experiments demonstrate that the NHP operation significantly improves performance, e.g., an ODS score reaching 0.818 on BSDS500, outperforming human performance (0.803), achieving state-of-the-art results in deep edge detection.
Databáze: Directory of Open Access Journals
načítá se...