Learning from the Tangram to Solve Mini Visual Tasks
Keywords:Computer Vision (CV), Machine Learning (ML)
AbstractCurrent pre-training methods in computer vision focus on natural images in the daily-life context. However, abstract diagrams such as icons and symbols are common and important in the real world. We are inspired by Tangram, a game that requires replicating an abstract pattern from seven dissected shapes. By recording human experience in solving tangram puzzles, we present the Tangram dataset and show that a pre-trained neural model on the Tangram helps solve some mini visual tasks based on low-resolution vision. Extensive experiments demonstrate that our proposed method generates intelligent solutions for aesthetic tasks such as folding clothes and evaluating room layouts. The pre-trained feature extractor can facilitate the convergence of few-shot learning tasks on human handwriting and improve the accuracy in identifying icons by their contours. The Tangram dataset is available at https://github.com/yizhouzhao/Tangram.
How to Cite
Zhao, Y., Qiu, L., Lu, P., Shi, F., Han, T., & Zhu, S.-C. (2022). Learning from the Tangram to Solve Mini Visual Tasks. Proceedings of the AAAI Conference on Artificial Intelligence, 36(3), 3490-3498. https://doi.org/10.1609/aaai.v36i3.20260
AAAI Technical Track on Computer Vision III