2020/08/27 by Alexander Wang, Wang, Alexander, Mengye Ren +3 · 2 citations
Computer Science · Mathematics · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE) #cs.CV #cs.LG #cs.NE #stat.ML
paper · pdf · doi:10.48550/arxiv.2009.04806
ICML 2021
arxiv created 2021/06/22 · arxiv updated 2021/06/24
Sketch drawings capture the salient information of visual concepts. Previous work has shown that neural networks are capable of producing sketches of natural objects drawn from a small number of classes. While earlier approaches focus on generation quality or retrieval, we explore properties of image representations learned by training a model to produce sketches of images. We show that this generative, class-agnostic model produces informative embeddings of images from novel examples, classes, and even novel datasets in a few-shot setting. Additionally, we find that these learned representations exhibit interesting structure and compositionality.