Construct · 1 fields · 1 citations

fooling images: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Computer vision

images that humans see as noise or abstract patterns but that networks classify as familiar objects with very high confidence.

In computer vision, fooling images refers to images that humans see as noise or abstract patterns but that networks classify as familiar objects with very high confidence. This meaning comes from Nguyen (2015) in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).[1]

Unit
Recovery means
Measured by

Run it through the Collider, or take the citations with you.

See how fooling images sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in Collider Export BibTeX Report this entry

Nearby constructs

confidence4 fields · 5 citationsjingle · one word, four constructs noise4 fields · 5 citationsjingle · one word, four constructs pattern recognition4 fields · 4 citationsjingle · one word, four constructs

References

Nguyen, A., Yosinski, J., & Clune, J. (2015). Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2015.7298640

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct