A Caltech Library Service

Scotopic Visual Recognition

Chen, Bo and Perona, Pietro (2015) Scotopic Visual Recognition. In: 2015 IEEE International Conference on Computer Vision Workshop (ICCVW). IEEE , Piscataway, NJ, pp. 659-662. ISBN 978-1-4673-9710-0.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


Recognition from a small number of photons is important for biomedical imaging, security, astronomy and many other fields. We develop a framework that allows a machine to classify objects as quickly as possible, hence requiring as few photons as possible, while maintaining the error rate below an acceptable threshold. The framework also allows for a dynamic speed versus accuracy tradeoff. Given a generative model of the scene, the optimal tradeoff can be obtained from a self-recurrent deep neural network. The generative model may also be learned from the data. We find that MNIST classification performance from less than 1 photon per pixel is comparable to that obtained from images in normal lighting conditions. Classification on CIFAR10 requires 10 photon per pixel to stay within 1% the normal-light performance.

Item Type:Book Section
Related URLs:
URLURL TypeDescription DOIArticle
Chen, Bo0000-0001-5566-7361
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2015 IEEE.
Record Number:CaltechAUTHORS:20160825-111046401
Persistent URL:
Official Citation:B. Chen and P. Perona, "Scotopic Visual Recognition," 2015 IEEE International Conference on Computer Vision Workshop (ICCVW), Santiago, 2015, pp. 659-662. doi: 10.1109/ICCVW.2015.88 URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:69944
Deposited By: Tony Diaz
Deposited On:25 Aug 2016 19:50
Last Modified:03 Oct 2019 10:26

Repository Staff Only: item control page