TransSketchNet: Attention-based Sketch Recognition using Transformers

Published in 24th European Conference on Artificial Intelligence (ECAI) 2020, At Santiago de Compostela, Spain, 2020

[ G. Jain, S. Chopra, S. Chopra ]*, and A. S. Parihar, "TransSketchNet: Attention-based Sketch Recognition using Transformers," To appear in 24th European Conference on Artificial Intelligence (ECAI) 2020, At Santiago de Compostela, Spain. (*Equal Contribution)

Abstract - Sketches have been employed since the ancient era of cave paintings for simple illustrations to represent real-world entities. The abstract nature and varied artistic styling makes automatic recognition of drawings more challenging than other areas of image classification. Moreover, the representation of sketches as a sequence of strokes instead of raster images introduces them at the correct abstract level. However, dealing with images as a sequence of small information makes it challenging. In this paper, we propose a Transformer-based network, dubbed as TransSketchNet, for sketch recognition. This architecture incorporates ordinal information to perform the classification task in real-time through vector images.

Download PDF