The Inclusive Images Competition

• Published in: The NeurIPS '18 Competition pp. 155 - 186
• Main Authors: Atwood, James, Halpern, Yoni, Baljekar, Pallavi, Breck, Eric, Sculley, D., Ostyakov, Pavel, Nikolenko, Sergey I., Ivanov, Igor, Solovyev, Roman, Wang, Weimin, Skalic, Miha
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2019; Springer International Publishing
• Series: The Springer Series on Challenges in Machine Learning
• ISBN: 9783030291341; 3030291340
• ISSN: 2520-131X; 2520-1328
• DOI: 10.1007/978-3-030-29135-8_6

Popular large image classification datasets that are drawn from the web present Eurocentric and Americentric biases that negatively impact the generalizability of models trained on them Shreya Shankar et al. (No classification without representation: Assessing geodiversity issues in open data sets for the developing world. arXiv preprint arXiv:1711.08536, 2017). In order to encourage the development of modeling approaches that generalize well to images drawn from locations and cultural contexts that are unseen or poorly represented at the time of training, we organized the Inclusive Images competition in association with Kaggle and the NeurIPS 2018 Competition Track Workshop. In this chapter, we describe the motivation and design of the competition, present reports from the top three competitors, and provide high-level takeaways from the competition results.