Methods › Computer Vision › Image Data Augmentation › RandAugment
RandAugment
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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 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.
Transformations applied include identity transformation, autoContrast, equalize, rotation, solarixation, colorjittering, posterizing, changing contrast, changing brightness, changing sharpness, shear-x, shear-y, translate-x, translate-y.
Papers archive 2025-07-28
30 shown of 67, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning 31 May 2025 · 0 repositories · arXiv:2506.00467
-
ZIPA: A family of efficient models for multilingual phone recognition 29 May 2025 · 1 repository · arXiv:2505.23170Syntology ran 0 of 1 samples · 1 unverified
-
HDC: Hierarchical Distillation for Multi-level Noisy Consistency in Semi-Supervised Fetal Ultrasound Segmentation 14 Apr 2025 · 0 repositories · arXiv:2504.09876
-
Learning Tree-Structured Composition of Data Augmentation 26 Aug 2024 · 1 repository · arXiv:2408.14381
-
Improving noisy student training for low-resource languages in End-to-End ASR using CycleGAN and inter-domain losses 26 Jul 2024 · 0 repositories · arXiv:2407.21061
-
Semi-supervised Learning for Code-Switching ASR with Large Language Model Filter 5 Jul 2024 · 0 repositories · arXiv:2407.04219
-
GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement 17 Jun 2024 · 2 repositories · arXiv:2406.11546Syntology ran 1 of 2 samples · 1 unverified
-
Self-Train Before You Transcribe 17 Jun 2024 · 1 repository · arXiv:2406.12937
-
Free Performance Gain from Mixing Multiple Partially Labeled Samples in Multi-label Image Classification 24 May 2024 · 0 repositories · arXiv:2405.15860
-
Conformer-1: Robust ASR via Large-Scale Semisupervised Bootstrapping 10 Apr 2024 · 0 repositories · arXiv:2404.07341
-
On the Effect of Image Resolution on Semantic Segmentation 8 Feb 2024 · 0 repositories · arXiv:2402.05398
-
Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR 17 Jan 2024 · 0 repositories · arXiv:2401.08992
-
Self-supervised Reflective Learning through Self-distillation and Online Clustering for Speaker Representation Learning 3 Jan 2024 · 0 repositories · arXiv:2401.01473
-
RandMSAugment: A Mixed-Sample Augmentation for Limited-Data Scenarios 25 Nov 2023 · 0 repositories · arXiv:2311.16508
-
Selective Volume Mixup for Video Action Recognition 18 Sep 2023 · 1 repository · arXiv:2309.09534
-
Automatic Data Augmentation Learning using Bilevel Optimization for Histopathological Images 21 Jul 2023 · 1 repository · arXiv:2307.11808Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
-
Tied-Augment: Controlling Representation Similarity Improves Data Augmentation 22 May 2023 · 1 repository · arXiv:2305.13520
-
Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets 6 Apr 2023 · 0 repositories · arXiv:2304.02847
-
Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification 4 Feb 2023 · 0 repositories · arXiv:2302.02070
-
From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search 16 Dec 2022 · 1 repository · arXiv:2212.08448
-
Self-Transriber: Few-shot Lyrics Transcription with Self-training 18 Nov 2022 · 0 repositories · arXiv:2211.10152
-
Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASR 11 Oct 2022 · 0 repositories · arXiv:2210.05793
-
Progress and limitations of deep networks to recognize objects in unusual poses 16 Jul 2022 · 1 repository · arXiv:2207.08034
-
FedNST: Federated Noisy Student Training for Automatic Speech Recognition 6 Jun 2022 · 0 repositories · arXiv:2206.02797
-
ReSmooth: Detecting and Utilizing OOD Samples when Training with Data Augmentation 25 May 2022 · 1 repository · arXiv:2205.12606
-
One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks 24 May 2022 · 1 repository · arXiv:2205.12141Syntology ran 4 of 18 samples · 14 unverified
-
Pseudo-Label Transfer from Frame-Level to Note-Level in a Teacher-Student Framework for Singing Transcription from Polyphonic Music 25 Mar 2022 · 1 repository · arXiv:2203.13422
-
Pseudo Label Is Better Than Human Label 22 Mar 2022 · 0 repositories · arXiv:2203.12668
-
Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation 19 Mar 2022 · 1 repository · arXiv:2203.10339
-
Deep AutoAugment 11 Mar 2022 · 1 repository · arXiv:2203.06172
Tasks archive 2025-07-28
20 shown of 89 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections