{"url":"/task/image-augmentation","name":"Image Augmentation","slug":"image-augmentation","description_markdown":"**Image Augmentation** is a data augmentation method that generates more training data from the existing training samples. Image Augmentation is especially useful in domains where training data is limited or expensive to obtain like in biomedical applications.\r\n\r\n<span class=\"description-source\">Source: [Improved Image Augmentation for Convolutional Neural Networks by Copyout and CopyPairing ](https://arxiv.org/abs/1909.00390)</span>\r\n\r\n( Image credit: [Kornia](https://github.com/kornia/kornia) )","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":308,"papers_with_code":127,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/image-augmentation-on-intel-image","slug":"image-augmentation-on-intel-image","dataset":"Intel Image Classification","dataset_url":"/dataset/intel-image-classification","rows_in_archive":1,"metrics":["Balanced Accuracy"],"first_row_in_archive_order":{"model":"Augstatic","paper_title":"AugStatic - A Light-Weight Image Augmentation Library","paper_url":"/paper/augstatic-a-light-weight-image-augmentation","paper_date":"2022-05-01","arxiv_id":null,"code_links":[{"title":"avs-abhishek123/AugStatic","url":"https://github.com/avs-abhishek123/AugStatic"}],"syntology":null}}],"datasets":[{"url":"/dataset/intel-image-classification","name":"Intel Image Classification","full_name":"","num_papers_in_archive":5}],"subtasks":[],"parent_tasks":[{"url":"/task/data-augmentation","name":"Data Augmentation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":127,"tagged_in_all":308,"items":[{"url":"/paper/autoaugment-learning-augmentation-policies","title":"AutoAugment: Learning Augmentation Policies from Data","date":"2018-05-24","arxiv_id":"1805.09501","repositories_listed":33,"syntology":{"n":43,"n_ran":6,"n_unverified":37,"n_pointer_only":2}},{"url":"/paper/improved-regularization-of-convolutional","title":"Improved Regularization of Convolutional Neural Networks with Cutout","date":"2017-08-15","arxiv_id":"1708.04552","repositories_listed":28,"syntology":{"n":24,"n_ran":21,"n_unverified":3,"n_pointer_only":5}},{"url":"/paper/unsupervised-data-augmentation-1","title":"Unsupervised Data Augmentation for Consistency Training","date":"2019-04-29","arxiv_id":"1904.12848","repositories_listed":20,"syntology":{"n":52,"n_ran":15,"n_unverified":37,"n_pointer_only":9}},{"url":"/paper/random-erasing-data-augmentation","title":"Random Erasing Data Augmentation","date":"2017-08-16","arxiv_id":"1708.04896","repositories_listed":18,"syntology":null},{"url":"/paper/fast-autoaugment","title":"Fast AutoAugment","date":"2019-05-01","arxiv_id":"1905.00397","repositories_listed":11,"syntology":{"n":40,"n_ran":22,"n_unverified":18,"n_pointer_only":3}},{"url":"/paper/learning-data-augmentation-strategies-for","title":"Learning Data Augmentation Strategies for Object Detection","date":"2019-06-26","arxiv_id":"1906.11172","repositories_listed":6,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/augmentor-an-image-augmentation-library-for","title":"Augmentor: An Image Augmentation Library for Machine Learning","date":"2017-08-11","arxiv_id":"1708.04680","repositories_listed":6,"syntology":null},{"url":"/paper/simple-copy-paste-is-a-strong-data","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","date":"2020-12-13","arxiv_id":"2012.07177","repositories_listed":5,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/kornia-an-open-source-differentiable-computer","title":"Kornia: an Open Source Differentiable Computer Vision Library for PyTorch","date":"2019-10-05","arxiv_id":"1910.02190","repositories_listed":5,"syntology":{"n":20,"n_ran":0,"n_unverified":20,"n_pointer_only":0}},{"url":"/paper/image-augmentation-is-all-you-need","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","date":"2020-04-28","arxiv_id":"2004.13649","repositories_listed":4,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":8}},{"url":"/paper/albumentations-fast-and-flexible-image","title":"Albumentations: fast and flexible image augmentations","date":"2018-09-18","arxiv_id":"1809.06839","repositories_listed":4,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/policy-gradient-driven-noise-mask","title":"Policy Gradient-Driven Noise Mask","date":"2024-04-29","arxiv_id":"2406.14568","repositories_listed":3,"syntology":null},{"url":"/paper/cascadetabnet-an-approach-for-end-to-end","title":"CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents","date":"2020-04-27","arxiv_id":"2004.12629","repositories_listed":3,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/learn-to-augment-joint-data-augmentation-and","title":"Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition","date":"2020-03-14","arxiv_id":"2003.06606","repositories_listed":3,"syntology":null},{"url":"/paper/190505393","title":"Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules","date":"2019-05-14","arxiv_id":"1905.05393","repositories_listed":3,"syntology":{"n":18,"n_ran":0,"n_unverified":18,"n_pointer_only":18}},{"url":"/paper/densenet-models-for-tiny-imagenet","title":"DenseNet Models for Tiny ImageNet Classification","date":"2019-04-23","arxiv_id":"1904.10429","repositories_listed":3,"syntology":null},{"url":"/paper/hard-view-selection-for-contrastive-learning","title":"Beyond Random Augmentations: Pretraining with Hard Views","date":"2023-10-05","arxiv_id":"2310.03940","repositories_listed":2,"syntology":null},{"url":"/paper/does-self-supervised-learning-really-improve","title":"Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?","date":"2022-06-10","arxiv_id":"2206.05266","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/deep-pcb-to-coco-convertor","title":"Deep PCB To COCO Convertor","date":"2022-05-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/improving-the-transferability-of-targeted","title":"Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input","date":"2022-03-17","arxiv_id":"2203.09123","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/detectron2-object-detection-manipulating","title":"Detectron2 Object Detection & Manipulating Images using Cartoonization","date":"2021-08-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/salient-objects-in-clutter","title":"Salient Objects in Clutter","date":"2021-05-07","arxiv_id":"2105.03053","repositories_listed":2,"syntology":null},{"url":"/paper/multi-disease-detection-in-retinal-imaging","title":"Multi-Disease Detection in Retinal Imaging based on Ensembling Heterogeneous Deep Learning Models","date":"2021-03-26","arxiv_id":"2103.14660","repositories_listed":2,"syntology":null},{"url":"/paper/fsce-few-shot-object-detection-via","title":"FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding","date":"2021-03-10","arxiv_id":"2103.05950","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/an-efficient-and-scalable-deep-learning","title":"An Efficient and Scalable Deep Learning Approach for Road Damage Detection","date":"2020-11-18","arxiv_id":"2011.09577","repositories_listed":2,"syntology":null},{"url":"/paper/prompt-free-conditional-diffusion-for-multi","title":"Prompt-Free Conditional Diffusion for Multi-object Image Augmentation","date":"2025-07-08","arxiv_id":"2507.06146","repositories_listed":1,"syntology":null},{"url":"/paper/when-large-multimodal-models-confront","title":"When Large Multimodal Models Confront Evolving Knowledge:Challenges and Pathways","date":"2025-05-30","arxiv_id":"2505.24449","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/language-driven-dual-style-mixing-for-single","title":"Language-Driven Dual Style Mixing for Single-Domain Generalized Object Detection","date":"2025-05-12","arxiv_id":"2505.07219","repositories_listed":1,"syntology":null},{"url":"/paper/batch-augmentation-with-unimodal-fine-tuning","title":"Batch Augmentation with Unimodal Fine-tuning for Multimodal Learning","date":"2025-05-10","arxiv_id":"2505.06592","repositories_listed":1,"syntology":null},{"url":"/paper/effective-dual-region-augmentation-for","title":"Effective Dual-Region Augmentation for Reduced Reliance on Large Amounts of Labeled Data","date":"2025-04-17","arxiv_id":"2504.13077","repositories_listed":1,"syntology":null}],"syntology_records":15,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}