Journal article

Publication year: 2020

Journal: Data in Brief

Volume number: 29

Open access status: Gold

DOI Link: https://doi.org/10.1016/j.dib.2020.105302

Publisher: Elsevier

Abstract: 

With the advent of deep convolutional neural networks, machines now rival humans in terms of object categorization. The neural networks solve categorization with a hierarchical organization that shares a striking resemblance to their biological counterpart, leading to their status as a standard model of object recognition in biological vision. Despite training on thousands of images of object categories, however, machine-learning networks are poorer generalizers, often fooled by adversarial images with very simple image manipulations that humans easily distinguish as a false image. Humans, on the other hand, can generalize object classes from very few samples. Here we provide a dataset of novel object classifications in humans. We gathered thousands of crowd-sourced human responses to novel objects embedded either with 1 or 16 context sample(s). Human decisions and stimuli together have the potential to be re-used (1) as a tool to better understand the nature of the gap in category learning from few samples between human and machine, and (2) as a benchmark of generalization across machine learning networks.

Harvard Citation style: Morgenstern, Y., Schmidt, F. and Fleming, R. (2020) A dataset for evaluating one-shot categorization of novel object classes, Data in Brief, 29, Article 105302. https://doi.org/10.1016/j.dib.2020.105302

APA Citation style: Morgenstern, Y., Schmidt, F., & Fleming, R. (2020). A dataset for evaluating one-shot categorization of novel object classes. Data in Brief. 29, Article 105302. https://doi.org/10.1016/j.dib.2020.105302