Current 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. This work is 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.
@article{arxiv.2112.06113,
title = {Learning from the Tangram to Solve Mini Visual Tasks},
author = {Yizhou Zhao and Liang Qiu and Pan Lu and Feng Shi and Tian Han and Song-Chun Zhu},
journal= {arXiv preprint arXiv:2112.06113},
year = {2021}
}