Figure 2 - uploaded by Samantha Arundel
Content may be subject to copyright.
Source publication
Maps are an important medium that enable people to comprehensively understand the configuration of cultural activities and natural elements over different times and places. Although massive maps are available in the digital era, how to effectively and accurately access the required map remains a challenge today. Previous works partially related to...
Contexts in source publication
Context 1
... we intend to apply DCNNs to classify map-types based on the map content when metadata and other auxiliary information (map title, map legend, etc.) are not available. Figure 2 shows a general architecture of a DCNN. ...
Context 2
... we intend to apply DCNNs to classify map-types based on the map content when metadata and other auxiliary information (map title, map legend, etc.) are not available. Figure 2 shows a general architecture of a DCNN. ...
Context 3
... machine learning (ML) approaches, or "shallow ML," have foundered when handling complex functions and features, and generally require substantial labor in training data to obtain satisfactory results (LeCun, Bengio and Hinton, 2015). Deep learning (DL) approaches enable computers to spontaneously access highly valuable information through unsupervised learning, and discover the high-level representations of data based on a multi-layered processing framework. In the last five years, a large number of DCNNs have produced impressive image classifications. Thus, we intend to apply DCNNs to classify map-types based on the map content when metadata and other auxiliary information (map title, map legend, etc.) are not available. Figure 2 shows a general architecture of a ...
