{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/recognition-in-terra-incognita","title":"Recognition in Terra Incognita","arxiv_id":"1807.04975","date":"2018-07-13","proceeding":"ECCV 2018 9","authors":["Sara Beery","Grant van Horn","Pietro Perona"],"abstract":"It is desirable for detection and classification algorithms to generalize to\nunfamiliar environments, but suitable benchmarks for quantitatively studying\nthis phenomenon are not yet available. We present a dataset designed to measure\nrecognition generalization to novel environments. The images in our dataset are\nharvested from twenty camera traps deployed to monitor animal populations.\nCamera traps are fixed at one location, hence the background changes little\nacross images; capture is triggered automatically, hence there is no human\nbias. The challenge is learning recognition in a handful of locations, and\ngeneralizing animal detection and classification to new locations where no\ntraining data is available. In our experiments state-of-the-art algorithms show\nexcellent performance when tested at the same location where they were trained.\nHowever, we find that generalization to new locations is poor, especially for\nclassification systems.","url_abs":"http://arxiv.org/abs/1807.04975v2","url_pdf":"http://arxiv.org/pdf/1807.04975v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"recognition-in-terra-incognita","repo_url":"https://github.com/deeplearning-wisc/hypo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"recognition-in-terra-incognita","repo_url":"https://github.com/facebookresearch/DomainBed","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"recognition-in-terra-incognita","repo_url":"https://github.com/facebookresearch/ModelRatatouille","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.04975","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}