SketchGAN: Joint Sketch Completion and Recognition with Generative Adversarial Network


Hand-drawn sketch recognition is a fundamental problem in computer vision, widely used in sketch-based image and video retrieval, editing, and reorganization. Previous methods often assume that a complete sketch is used as input; however, hand-drawn sketches in common application scenarios are often incomplete, which makes sketch recognition a challenging problem.

A research team led by Prof. Cuixia Ma from Institute of Software of Chinese Academy of Sciences (CAS) proposes SketchGAN, a new generative adversarial network (GAN) based approach that jointly completes and recognizes a sketch, boosting the performance of both tasks.

Prof. Cuixia Ma and her co-authors use a cascade Encode-Decoder network to complete the input sketch in an iterative manner, and employ an auxiliary sketch recognition task to recognize the completed sketch.

Prof. Cuixia Ma and her co-authors are the first to solve the problem of sketch completion, which can inspire further sketch-based research. The proposed network architecture is able to handle sketches of different categories. SketchGAN jointly conducts sketch completion and an auxiliary sketch recognition task, and it has been found that these two tasks benefit each other.
Experiments on the Sketchy database benchmark demonstrate that the joint learning approach achieves competitive sketch completion and recognition performance compared with the state-of-the-art methods. 

The study entitled "SketchGAN: Joint Sketch Completion and Recognition with Generative Adversarial Network" has been published in IEEE Conference on Computer Vision and Pattern Recognition.