Dataset Open Access

A dataset for evaluating one-shot categorization of novel object classes

Morgenstern, Yaniv; Schmidt, Filipp; Fleming, Roland

From just a single example, we can derive quite precise intuitions about what other class members look like.  This stands in stark contrast to machine learning algorithms, which typically require tens or even hundreds of thousands of examples to learn a new category.  One of the most important open questions in our field is: How do humans achieve this? The stimuli and data provided here (in MATLAB format) are from thousands of crowd-sourced human responses to novel objects.   The data can be used to test machine learning generalization as compared to human and also can be used as a test bed for various kinds of category learning models. 

Files (151.9 MB)
Name Size
151.9 MB Download
All versions This version
Views 9936
Downloads 102
Data volume 1.5 GB303.7 MB
Unique views 8029
Unique downloads 92


Cite as