Edge Augmentation for Large-Scale Sketch Recognition without Sketches

TL;DR

This paper introduces a novel data augmentation method that converts natural images into a pseudo-sketch domain, enabling large-scale CNN training for sketch recognition across over twice as many categories as previous methods.

Contribution

It presents a new augmentation technique called randomized Binary Thin Edges (rBTE) that bridges the domain gap between natural images and sketches for large-scale recognition.

Findings

Successful training on 874 natural image categories

Recognition performance on a subset of 393 sketch categories

Scalability to more than 2.5 times larger category sets

Abstract

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.