English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep networks have achieved excellent results in perceptual tasks, yet theirability to generalize to variations not seen during training has come underincreasing scrutiny. In this work we focus on their ability to have invariancetowards the presence or absence of details. For example, humans are able towatch cartoons, which are missing many visual details, without being explicitlytrained to do so. As another example, 3D rendering software is a relativelyrecent development, yet people are able to understand such rendered scenes eventhough they are missing details (consider a film like Toy Story). The failureof machine learning algorithms to do this indicates a significant gap ingeneralization between human abilities and the abilities of deep networks. Wepropose a dataset that will make it easier to study the detail-invarianceproblem concretely. We produce a concrete task for this: SketchTransfer, and weshow that state-of-the-art domain transfer algorithms still struggle with thistask. The state-of-the-art technique which achieves over 95\% on MNIST$\xrightarrow{}$ SVHN transfer only achieves 59\% accuracy on theSketchTransfer task, which is much better than random (11\% accuracy) but fallsshort of the 87\% accuracy of a classifier trained directly on labeledsketches. This indicates that this task is approachable with today's bestmethods but has substantial room for improvement.

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