Persons
Ing. Nikolaos Efthymiadis
All publications
Edge Augmentation for Large-Scale Sketch Recognition without Sketches
- Authors: Ing. Nikolaos Efthymiadis, doc. Georgios Tolias, Ph.D., prof. Mgr. Ondřej Chum, Ph.D.,
- Publication: 2022 26th International Conference on Pattern Recognition (ICPR). Piscataway: IEEE, 2022. p. 3595-3602. ISSN 2831-7475. ISBN 978-1-6654-9062-7.
- Year: 2022
- DOI: 10.1109/ICPR56361.2022.9956233
- Link: https://doi.org/10.1109/ICPR56361.2022.9956233
- Department: Visual Recognition Group
-
Annotation:
This work addresses scaling up the sketch classification task into a large number of categories. Collecting sketches for training is a slow and tedious process that has so far precluded any attempts to large-scale sketch recognition. We overcome the lack of training sketch data by exploiting labeled collections of natural images that are easier to obtain. To bridge the domain gap we present a novel augmentation technique that is tailored to the task of learning sketch recognition from a training set of natural images. Randomization is introduced in the parameters of edge detection and edge selection. Natural images are translated to a pseudo-novel domain called "randomized Binary Thin Edges" (rBTE), which is used as a training domain instead of natural images. The ability to scale up is demonstrated by training CNN-based sketch recognition of more than 2.5 times larger number of categories than used previously. For this purpose, a dataset of natural images from 874 categories is constructed by combining a number of popular computer vision datasets. The categories are selected to be suitable for sketch recognition. To estimate the performance, a subset of 393 categories with sketches is also collected.