Posted on December 25, 2019 | Back to Showreel

SketchTransfer - A Challenging New Task for Exploring Detail-Invariance and the Abstractions Learned by Deep Networks

Tags: dataset | Paper

This isn’t a network itself; it’s a dataset and a proposed task. The idea of this dataset is that there is definitely a similarity between sketches of real objects, and photos of those objects; but, neural networks aren’t great at knowing this abstraction, yet. I.e. If I have an object-classifier, it can’t very well classify sketches. We’ll see how people progress towards this problem via this dataset!