Timezone: »

 
Poster
SketchEmbedNet: Learning Novel Concepts by Imitating Drawings
Alexander Wang · Mengye Ren · Richard Zemel

Thu Jul 22 09:00 AM -- 11:00 AM (PDT) @
in Poster Session 5 »

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.

Keywords: Neuroscience and Cognitive Science · Human or Animal Learning · Neuroscience and Cognitive Science -> Memory; Optimization -> Combinatorial Optimization; Optimization · Submodular Optimizati · Embedding and Representation learning

Author Information

Alexander Wang (University of Toronto)
Mengye Ren (Uber ATG / University of Toronto)
Richard Zemel (Vector Institute)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors