S
Sara Beery
Researcher at California Institute of Technology
Publications - 34
Citations - 1831
Sara Beery is an academic researcher from California Institute of Technology. The author has contributed to research in topics: Population & Computer science. The author has an hindex of 13, co-authored 29 publications receiving 592 citations. Previous affiliations of Sara Beery include Google & Seattle University.
Papers
More filters
Posted Content
WILDS: A Benchmark of in-the-Wild Distribution Shifts
Pang Wei Koh,Shiori Sagawa,Henrik Marklund,Sang Michael Xie,Marvin Zhang,Akshay Balsubramani,Weihua Hu,Michihiro Yasunaga,Richard Lanas Phillips,Irena Gao,Tony Lee,Etienne David,Ian Stavness,Wei Guo,Berton A. Earnshaw,Imran S. Haque,Sara Beery,Jure Leskovec,Anshul Kundaje,Emma Pierson,Sergey Levine,Chelsea Finn,Percy Liang +22 more
TL;DR: WILDS is presented, a benchmark of in-the-wild distribution shifts spanning diverse data modalities and applications, and is hoped to encourage the development of general-purpose methods that are anchored to real-world distribution shifts and that work well across different applications and problem settings.
Posted Content
Recognition in Terra Incognita
TL;DR: 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, so a dataset designed to measure recognition generalization to novel environments is presented.
Book ChapterDOI
Recognition in Terra Incognita
TL;DR: The CaltechCameraTraps dataset as mentioned in this paper is designed to measure recognition generalization to novel environments, where cameras are fixed at one location, hence the background changes little across images; capture is triggered automatically, hence there is no human bias.
Proceedings ArticleDOI
Benchmarking Representation Learning for Natural World Image Collections
TL;DR: In this paper, the authors present two new natural world visual classification datasets, iNat2021 and NeWT, with the aim of benchmarking the performance of representation learning algorithms on a suite of challenging natural world binary classification tasks that go beyond standard species classification.
Journal ArticleDOI
A deep active learning system for species identification and counting in camera trap images
Mohammad Sadegh Norouzzadeh,Mohammad Sadegh Norouzzadeh,Dan Morris,Sara Beery,Sara Beery,Neel Joshi,Nebojsa Jojic,Jeff Clune,Jeff Clune +8 more
TL;DR: This paper combines the power of machine intelligence and human intelligence via a novel active learning system to minimize the manual work required to train a computer vision model, and is the first work to apply an active learning approach to camera trap images.