Papers with Code 아카이브
Data Augmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 3
- 보존된 평가 기록
- 26
Data augmentation involves techniques used for increasing the amount of data, based on different modifications, to expand the amount of examples in the original dataset. Data augmentation not only helps to grow the dataset but it also increases the diversity of the dataset. When training machine learning models, data augmentation acts as a regularizer and helps to avoid overfitting.
Data augmentation techniques have been found useful in domains like NLP and computer vision. In computer vision, transformations like cropping, flipping, and rotation are used. In NLP, data augmentation techniques can include swapping, deletion, random insertion, among others.
Further readings:
- A Survey of Data Augmentation Approaches for NLP
- A survey on Image Data Augmentation for Deep Learning
<span style="color:grey; opacity: 0.6">( Image credit: Albumentations )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/deqingfu/scene
공식 코드SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples
https://github.com/derekabc/gans-agriculture
공식 코드Generative Adversarial Networks for Image Augmentation in Agriculture: A Systematic Review
https://github.com/derekchen14/mixture_soft_prompts
공식 코드https://github.com/deshwalmahesh/PHUDGE
공식 코드https://github.com/dessertlab/robustness-of-ai-offensive-code-generators
공식 코드Enhancing Robustness of AI Offensive Code Generators via Data Augmentation
https://github.com/devavrattomar/sst
공식 코드Self-Supervised Generative Style Transfer for One-Shot Medical Image Segmentation
https://github.com/devinamhn/radiogalaxies-bbb
공식 코드Weight Pruning and Uncertainty in Radio Galaxy Classification
https://github.com/devjake/eeg-diffusion-pytorch
공식 코드EEG Synthetic Data Generation Using Probabilistic Diffusion Models
https://github.com/devnkong/FLAG
공식 코드Robust Optimization as Data Augmentation for Large-scale Graphs
https://github.com/dheeraj7596/conda
공식 코드Leveraging QA Datasets to Improve Generative Data Augmentation
https://github.com/dheeraj7596/qagen
공식 코드Leveraging QA Datasets to Improve Generative Data Augmentation
https://github.com/dhyuan99/veckm_flow
공식 코드https://github.com/dial-rpi/spectral-adversarial-data-augmentation
공식 코드When Neural Networks Fail to Generalize? A Model Sensitivity Perspective
https://github.com/diaoenmao/semifl-semi-supervised-federated-learning-for-unlabeled-clients-with-alternate-training
공식 코드SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training
https://github.com/diffusion-model-leiden/awesome-diffusion-models-for-tabular-data
공식 코드Diffusion Models for Tabular Data: Challenges, Current Progress, and Future Directions
https://github.com/dilis-lab/simbaml_examples
공식 코드SimbaML: Connecting Mechanistic Models and Machine Learning with Augmented Data
https://github.com/dinghanshen/Cutoff
공식 코드https://github.com/dipta007/semeval24-task8
공식 코드https://github.com/dipuk0506/multimodal
공식 코드Batch Augmentation with Unimodal Fine-tuning for Multimodal Learning
https://github.com/disl-lab/balancemix
공식 코드https://github.com/distributionnetworkstudelft/rl-adn
공식 코드https://github.com/divelab/DIG
공식 코드https://github.com/djidje/D-MMD
공식 코드Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification
https://github.com/dkalpakchi/ud_parser_consistency
공식 코드Minor changes make a difference: a case study on the consistency of UD-based dependency parsers
https://github.com/dkaushik96/bizarro-data
공식 코드Learning the Difference that Makes a Difference with Counterfactually-Augmented Data
https://github.com/dkaushik96/counterfactually-augmented-data
공식 코드Learning the Difference that Makes a Difference with Counterfactually-Augmented Data
https://github.com/dlmacedo/entropic-out-of-distribution-detection
공식 코드https://github.com/dlongry/solution-to-cvpr2021-nas-track2
공식 코드Cascade Bagging for Accuracy Prediction with Few Training Samples
https://github.com/dm2-nd/eland
공식 코드Action Sequence Augmentation for Early Graph-based Anomaly Detection
https://github.com/dmey/synthia
공식 코드Copula-based synthetic data augmentation for machine-learning emulators
https://github.com/dobriban/data_aug
공식 코드https://github.com/dogabasaran/lesion-synthesis
공식 코드Subject-Specific Lesion Generation and Pseudo-Healthy Synthesis for Multiple Sclerosis Brain Images
https://github.com/dogabasaran/lesionmix
공식 코드LesionMix: A Lesion-Level Data Augmentation Method for Medical Image Segmentation
https://github.com/dogyoonlee/RSMix-official
공식 코드Regularization Strategy for Point Cloud via Rigidly Mixed Sample
https://github.com/dongchen06/dmweeds
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.