OLX Group operates a network of online trading platforms in over 40 countries under market-leading brands such as Avito, dubizzle, letgo, OLX, Stradia, Storia, and more, that are used by over 300 million people every month to buy and sell almost anything, creating win-win exchanges for people, their communities and the environment. OLX Group is a part of Naspers. Founded in 1915, Naspers is a global internet and entertainment group and one of the largest technology investors in the world. Operating in more than 120 countries and markets with long-term growth potential, Naspers builds leading companies that empower people and enrich communities. It runs some of the world’s leading platforms in internet, video entertainment, and media. The Personalization & Relevance team at OLX is increasing transactions between buyers and sellers by showing the most relevant content to our users. We are developing personalization technologies and optimization strategies that fuel the discovery of new items and have a direct impact on OLX’s bottom line. A picture is worth a thousand words: OLX is a gold mine for unique hard to find items. We are researching deep learning techniques to make it easier for sellers to describe the item they are selling.
Your task is to implement a solution to predict the category of an item based on one or multiple images of the item. We provide two datasets containing items from the same category. In dataset 1, the items are further split into 400 sub-categories and are represented by stock photos. In dataset 2, the items are split into 15 sub-categories and are represented by user-generated photos. The solution shall allow modifying and adding categories without significant retraining. It shall also support transfer learning from model trained on dataset 1 to dataset 2.