{"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/trivialaugment-tuning-free-yet-state-of-the","title":"TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation","arxiv_id":"2103.10158","date":"2021-03-18","proceeding":"ICCV 2021 10","authors":["Samuel G. Müller","Frank Hutter"],"abstract":"Automatic augmentation methods have recently become a crucial pillar for strong model performance in vision tasks. While existing automatic augmentation methods need to trade off simplicity, cost and performance, we present a most simple baseline, TrivialAugment, that outperforms previous methods for almost free. TrivialAugment is parameter-free and only applies a single augmentation to each image. Thus, TrivialAugment's effectiveness is very unexpected to us and we performed very thorough experiments to study its performance. First, we compare TrivialAugment to previous state-of-the-art methods in a variety of image classification scenarios. Then, we perform multiple ablation studies with different augmentation spaces, augmentation methods and setups to understand the crucial requirements for its performance. Additionally, we provide a simple interface to facilitate the widespread adoption of automatic augmentation methods, as well as our full code base for reproducibility. Since our work reveals a stagnation in many parts of automatic augmentation research, we end with a short proposal of best practices for sustained future progress in automatic augmentation methods.","url_abs":"https://arxiv.org/abs/2103.10158v2","url_pdf":"https://arxiv.org/pdf/2103.10158v2.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":"trivialaugment-tuning-free-yet-state-of-the","repo_url":"https://github.com/pytorch/vision","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"trivialaugment-tuning-free-yet-state-of-the","repo_url":"https://github.com/automl/trivialaugment","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/data-augmentation-on-imagenet","task":"Data Augmentation","dataset":"ImageNet","model":"ResNet-50 (TA wide)","rank_in_archive_order":8,"of":17,"metrics":{"Accuracy (%)":"78.07"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.10158","atlas_url":"https://app.syntology.ai/?focus=2103.10158","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}