A Caltech Library Service

Recognition in Terra Incognita

Beery, Sara and Van Horn, Grant and Perona, Pietro (2018) Recognition in Terra Incognita. In: Computer Vision – ECCV 2018. Lecture Notes in Computer Science. Vol.16. No.11220. Springer Nature Switzerland AG , Cham, Switzerland, pp. 472-489. ISBN 978-3-030-01269-4.

[img] PDF (Computer Vision Foundation) - Accepted Version
See Usage Policy.

[img] PDF (arXiv) - Accepted Version
See Usage Policy.

[img] PDF - Supplemental Material
See Usage Policy.


Use this Persistent URL to link to this item:


It is desirable for detection and classification algorithms to generalize to unfamiliar environments, but suitable benchmarks for quantitatively studying this phenomenon are not yet available. We present a dataset designed to measure recognition generalization to novel environments. The images in our dataset are harvested from twenty camera traps deployed to monitor animal populations. Camera traps are fixed at one location, hence the background changes little across images; capture is triggered automatically, hence there is no human bias. The challenge is learning recognition in a handful of locations, and generalizing animal detection and classification to new locations where no training data is available. In our experiments state-of-the-art algorithms show excellent performance when tested at the same location where they were trained. However, we find that generalization to new locations is poor, especially for classification systems. (The dataset is available at

Item Type:Book Section
Related URLs:
URLURL TypeDescription Paper ItemDataset
Beery, Sara0000-0002-2544-1844
Perona, Pietro0000-0002-7583-5809
Additional Information:© Springer Nature Switzerland AG 2018. We would like to thank the USGS and NPS for providing data. This work was supported by NSFGRFP Grant No. 1745301, the views are those of the authors and do not necessarily reflect the views of the NSF. Compute time was provided by an AWS Research Grant.
Funding AgencyGrant Number
NSF Graduate Research FellowshipDGE-1745301
Amazon Web ServicesUNSPECIFIED
Subject Keywords:Recognition, transfer learning, domain adaptation, context, dataset, benchmark
Series Name:Lecture Notes in Computer Science
Issue or Number:11220
Record Number:CaltechAUTHORS:20190327-085924057
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94202
Deposited By: George Porter
Deposited On:27 Mar 2019 16:51
Last Modified:16 Nov 2021 17:03

Repository Staff Only: item control page