Generic Sketch-Based Retrieval Learned without Drawing a Single Sketch.
Year: 2017
Type: preprint
Abstract: We cast the sketch-based retrieval as edge-map matching. A shared convolutional network is trained to extract descriptors from edge maps and sketches, which are treated as a special case of edge maps. The network is fine-tuned solely from edge maps of landmark images. The training images are acquired in a fully unsupervised manner from 3D landmark models obtained by an automated structure-from-motion pipeline.
The proposed method achieves the state-of-the-art results on a standard benchmark. On two other fine-grained sketch-based retrieval benchmarks, it performs on par with or comes just after the method specifically designed for the dataset.
Source: arXiv (Cornell University)
Authors: Filip Radenović, Giorgos Tolias, Ondřej Chum
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2755089964