CaltechAUTHORS
  A Caltech Library Service

Presence-Only Geographical Priors for Fine-Grained Image Classification

Mac Aodha, Oisin and Cole, Elijah and Perona, Pietro (2019) Presence-Only Geographical Priors for Fine-Grained Image Classification. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE , Piscataway, NJ, pp. 9595-9605. ISBN 9781728148038. https://resolver.caltech.edu/CaltechAUTHORS:20200306-091556702

[img] PDF - Submitted Version
See Usage Policy.

2838Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200306-091556702

Abstract

Appearance information alone is often not sufficient to accurately differentiate between fine-grained visual categories. Human experts make use of additional cues such as where, and when, a given image was taken in order to inform their final decision. This contextual information is readily available in many online image collections but has been underutilized by existing image classifiers that focus solely on making predictions based on the image contents. We propose an efficient spatio-temporal prior, that when conditioned on a geographical location and time, estimates the probability that a given object category occurs at that location. Our prior is trained from presence-only observation data and jointly models object categories, their spatio-temporal distributions, and photographer biases. Experiments performed on multiple challenging image classification datasets show that combining our prior with the predictions from image classifiers results in a large improvement in final classification performance.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/iccv.2019.00969DOIArticle
https://arxiv.org/abs/1906.05272arXivDiscussion Paper
ORCID:
AuthorORCID
Mac Aodha, Oisin0000-0002-5787-5073
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2019 IEEE. This work was supported by a Google Focused Research Award and an NSF Graduate Research Fellowship (Grant No. DGE1745301). We thank Grant Van Horn and Serge Belongie for helpful discussions, along with NVIDIA and AWS for their kind donations.
Funders:
Funding AgencyGrant Number
GoogleUNSPECIFIED
NSF Graduate Research FellowshipDGE-1745301
NVIDIAUNSPECIFIED
Amazon Web ServicesUNSPECIFIED
Record Number:CaltechAUTHORS:20200306-091556702
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200306-091556702
Official Citation:O. M. Aodha, E. Cole and P. Perona, "Presence-Only Geographical Priors for Fine-Grained Image Classification," 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019, pp. 9595-9605. doi: 10.1109/ICCV.2019.00969
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:101735
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:06 Mar 2020 17:24
Last Modified:06 Mar 2020 23:20

Repository Staff Only: item control page