{"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/the-freiburg-groceries-dataset","title":"The Freiburg Groceries Dataset","arxiv_id":"1611.05799","date":"2016-11-17","proceeding":null,"authors":["Philipp Jund","Nichola Abdo","Andreas Eitel","Wolfram Burgard"],"abstract":"With the increasing performance of machine learning techniques in the last\nfew years, the computer vision and robotics communities have created a large\nnumber of datasets for benchmarking object recognition tasks. These datasets\ncover a large spectrum of natural images and object categories, making them not\nonly useful as a testbed for comparing machine learning approaches, but also a\ngreat resource for bootstrapping different domain-specific perception and\nrobotic systems. One such domain is domestic environments, where an autonomous\nrobot has to recognize a large variety of everyday objects such as groceries.\nThis is a challenging task due to the large variety of objects and products,\nand where there is great need for real-world training data that goes beyond\nproduct images available online. In this paper, we address this issue and\npresent a dataset consisting of 5,000 images covering 25 different classes of\ngroceries, with at least 97 images per class. We collected all images from\nreal-world settings at different stores and apartments. In contrast to existing\ngroceries datasets, our dataset includes a large variety of perspectives,\nlighting conditions, and degrees of clutter. Overall, our images contain\nthousands of different object instances. It is our hope that machine learning\nand robotics researchers find this dataset of use for training, testing, and\nbootstrapping their approaches. As a baseline classifier to facilitate\ncomparison, we re-trained the CaffeNet architecture (an adaptation of the\nwell-known AlexNet) on our dataset and achieved a mean accuracy of 78.9%. We\nrelease this trained model along with the code and data splits we used in our\nexperiments.","url_abs":"http://arxiv.org/abs/1611.05799v1","url_pdf":"http://arxiv.org/pdf/1611.05799v1.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":"the-freiburg-groceries-dataset","repo_url":"https://github.com/PhilJd/freiburg_groceries_dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"the-freiburg-groceries-dataset","repo_url":"https://github.com/AwesumMe/RetailClassification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[{"slug":"freiburg-groceries","name":"Freiburg Groceries","full_name":"Freiburg Groceries"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1611.05799","atlas_url":"https://app.syntology.ai/?focus=1611.05799","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}