{"url":"/method/randaugment","slug":"randaugment","name":"RandAugment","full_name":"RandAugment","full_name_withheld":false,"description_markdown":"**RandAugment** is an automated data augmentation method. The search space for data augmentation has 2 interpretable hyperparameter $N$ and $M$.  $N$ is the number of augmentation transformations to apply sequentially, and $M$ is the magnitude for all the transformations. To reduce the parameter space but still maintain image diversity, learned policies and probabilities for applying each transformation are replaced with a parameter-free procedure of always selecting a transformation with uniform probability $\\frac{1}{K}$. Here $K$ is the number of transformation options. So given $N$ transformations for a training image, RandAugment may thus express $KN$ potential policies.\r\n\r\nTransformations applied include identity transformation, autoContrast, equalize, rotation, solarixation, colorjittering, posterizing, changing contrast, changing brightness, changing sharpness, shear-x, shear-y, translate-x, translate-y.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/1909.13719v2","title":"RandAugment: Practical automated data augmentation with a reduced search space","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/ildoonet/pytorch-randaugment","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Data Augmentation","url":"/methods/category/image-data-augmentation","pwc_aliases":[]}],"n_papers_tagged":67,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/sst-self-training-with-self-adaptive-1","title":"SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning","date":"2025-05-31","arxiv_id":"2506.00467","n_code_links":0,"syntology":null},{"paper":"/paper/zipa-a-family-of-efficient-models-for","title":"ZIPA: A family of efficient models for multilingual phone recognition","date":"2025-05-29","arxiv_id":"2505.23170","n_code_links":1,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":0}},{"paper":null,"title":"HDC: Hierarchical Distillation for Multi-level Noisy Consistency in Semi-Supervised Fetal Ultrasound Segmentation","date":"2025-04-14","arxiv_id":"2504.09876","n_code_links":0,"syntology":null},{"paper":"/paper/learning-tree-structured-composition-of-data","title":"Learning Tree-Structured Composition of Data Augmentation","date":"2024-08-26","arxiv_id":"2408.14381","n_code_links":1,"syntology":null},{"paper":null,"title":"Improving noisy student training for low-resource languages in End-to-End ASR using CycleGAN and inter-domain losses","date":"2024-07-26","arxiv_id":"2407.21061","n_code_links":0,"syntology":null},{"paper":null,"title":"Semi-supervised Learning for Code-Switching ASR with Large Language Model Filter","date":"2024-07-05","arxiv_id":"2407.04219","n_code_links":0,"syntology":null},{"paper":"/paper/gigaspeech-2-an-evolving-large-scale-and","title":"GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement","date":"2024-06-17","arxiv_id":"2406.11546","n_code_links":2,"syntology":{"ran":1,"of":2,"unverified":1,"pointer_only":0}},{"paper":"/paper/self-train-before-you-transcribe","title":"Self-Train Before You Transcribe","date":"2024-06-17","arxiv_id":"2406.12937","n_code_links":1,"syntology":null},{"paper":null,"title":"Free Performance Gain from Mixing Multiple Partially Labeled Samples in Multi-label Image Classification","date":"2024-05-24","arxiv_id":"2405.15860","n_code_links":0,"syntology":null},{"paper":null,"title":"Conformer-1: Robust ASR via Large-Scale Semisupervised Bootstrapping","date":"2024-04-10","arxiv_id":"2404.07341","n_code_links":0,"syntology":null},{"paper":null,"title":"On the Effect of Image Resolution on Semantic Segmentation","date":"2024-02-08","arxiv_id":"2402.05398","n_code_links":0,"syntology":null},{"paper":null,"title":"Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR","date":"2024-01-17","arxiv_id":"2401.08992","n_code_links":0,"syntology":null},{"paper":null,"title":"Self-supervised Reflective Learning through Self-distillation and Online Clustering for Speaker Representation Learning","date":"2024-01-03","arxiv_id":"2401.01473","n_code_links":0,"syntology":null},{"paper":null,"title":"RandMSAugment: A Mixed-Sample Augmentation for Limited-Data Scenarios","date":"2023-11-25","arxiv_id":"2311.16508","n_code_links":0,"syntology":null},{"paper":"/paper/selective-volume-mixup-for-video-action","title":"Selective Volume Mixup for Video Action Recognition","date":"2023-09-18","arxiv_id":"2309.09534","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-data-augmentation-learning-using","title":"Automatic Data Augmentation Learning using Bilevel Optimization for Histopathological Images","date":"2023-07-21","arxiv_id":"2307.11808","n_code_links":1,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":1}},{"paper":"/paper/tied-augment-controlling-representation","title":"Tied-Augment: Controlling Representation Similarity Improves Data Augmentation","date":"2023-05-22","arxiv_id":"2305.13520","n_code_links":1,"syntology":null},{"paper":null,"title":"Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets","date":"2023-04-06","arxiv_id":"2304.02847","n_code_links":0,"syntology":null},{"paper":null,"title":"Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification","date":"2023-02-04","arxiv_id":"2302.02070","n_code_links":0,"syntology":null},{"paper":"/paper/from-xception-to-nexception-new-design","title":"From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search","date":"2022-12-16","arxiv_id":"2212.08448","n_code_links":1,"syntology":null},{"paper":null,"title":"Self-Transriber: Few-shot Lyrics Transcription with Self-training","date":"2022-11-18","arxiv_id":"2211.10152","n_code_links":0,"syntology":null},{"paper":null,"title":"Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASR","date":"2022-10-11","arxiv_id":"2210.05793","n_code_links":0,"syntology":null},{"paper":"/paper/progress-and-limitations-of-deep-networks-to","title":"Progress and limitations of deep networks to recognize objects in unusual poses","date":"2022-07-16","arxiv_id":"2207.08034","n_code_links":1,"syntology":null},{"paper":null,"title":"FedNST: Federated Noisy Student Training for Automatic Speech Recognition","date":"2022-06-06","arxiv_id":"2206.02797","n_code_links":0,"syntology":null},{"paper":"/paper/resmooth-detecting-and-utilizing-ood-samples","title":"ReSmooth: Detecting and Utilizing OOD Samples when Training with Data Augmentation","date":"2022-05-25","arxiv_id":"2205.12606","n_code_links":1,"syntology":null},{"paper":"/paper/one-pixel-shortcut-on-the-learning-preference","title":"One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks","date":"2022-05-24","arxiv_id":"2205.12141","n_code_links":1,"syntology":{"ran":4,"of":18,"unverified":14,"pointer_only":0}},{"paper":"/paper/pseudo-label-transfer-from-frame-level-to","title":"Pseudo-Label Transfer from Frame-Level to Note-Level in a Teacher-Student Framework for Singing Transcription from Polyphonic Music","date":"2022-03-25","arxiv_id":"2203.13422","n_code_links":1,"syntology":null},{"paper":null,"title":"Pseudo Label Is Better Than Human Label","date":"2022-03-22","arxiv_id":"2203.12668","n_code_links":0,"syntology":null},{"paper":"/paper/occlusion-aware-self-supervised-monocular-6d","title":"Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation","date":"2022-03-19","arxiv_id":"2203.10339","n_code_links":1,"syntology":null},{"paper":"/paper/deep-autoaugment-1","title":"Deep AutoAugment","date":"2022-03-11","arxiv_id":"2203.06172","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/data-augmentation","name":"Data Augmentation","papers":24},{"task":"/task/image-classification","name":"Image Classification","papers":17},{"task":"/task/image-classification","name":"image-classification","papers":13},{"task":"/task/speech-recognition","name":"Speech Recognition","papers":10},{"task":"/task/speech-recognition-1","name":"speech-recognition","papers":10},{"task":"/task/automatic-speech-recognition-2","name":"Automatic Speech Recognition","papers":8},{"task":"/task/automatic-speech-recognition","name":"Automatic Speech Recognition (ASR)","papers":7},{"task":"/task/segmentation","name":"Segmentation","papers":6},{"task":"/task/diversity","name":"Diversity","papers":5},{"task":"/task/classification","name":"General Classification","papers":4},{"task":"/task/pseudo-label","name":"Pseudo Label","papers":4},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":4},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":4},{"task":"/task/classification-1","name":"Classification","papers":3},{"task":"/task/image-augmentation","name":"Image Augmentation","papers":3},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":3},{"task":"/task/object-detection","name":"Object Detection","papers":3},{"task":"/task/object-detection-1","name":"object-detection","papers":3},{"task":"/task/computed-tomography-ct","name":"Computed Tomography (CT)","papers":2},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":2}],"tasks_shown":20,"n_tasks":89,"usage_by_year":[{"year":"2019","papers":2},{"year":"2020","papers":16},{"year":"2021","papers":18},{"year":"2022","papers":12},{"year":"2023","papers":6},{"year":"2024","papers":10},{"year":"2025","papers":3}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/randaugment"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}