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/AlexeyAB/darknet
공식 코드https://github.com/Alexuan/musical_instrument_embedding
공식 코드https://github.com/AliOsm/semantic-question-similarity
공식 코드Tha3aroon at NSURL-2019 Task 8: Semantic Question Similarity in Arabic
https://github.com/AliaksandrSiarohin/pose-gan
공식 코드Appearance and Pose-Conditioned Human Image Generation using Deformable GANs
https://github.com/AmirAbaskohi/Persian-Emotion-Detection-using-ParsBERT-and-Imbalanced-Data-Handling-Approaches
공식 코드Persian Emotion Detection using ParsBERT and Imbalanced Data Handling Approaches
https://github.com/Amirhossein-Nayebi/Nordic-Vehicle-Dataset
공식 코드https://github.com/AndrewPBerg/UAV_Classification
공식 코드15,500 Seconds: Lean UAV Classification Leveraging PEFT and Pre-Trained Networks
https://github.com/Anmol2059/NLPineers
공식 코드https://github.com/Anmol2059/NLPineers_Chipsal
공식 코드https://github.com/AnonymousDLMA/MI_with_DA
공식 코드How Does Data Augmentation Affect Privacy in Machine Learning?
https://github.com/Arksyd96/synthesis-with-slice-based-ldm
공식 코드https://github.com/ArnabKumarRoy02/ResEmoteNet
공식 코드Improvement in Facial Emotion Recognition using Synthetic Data Generated by Diffusion Model
https://github.com/AslanDing/AutoTCL
공식 코드Parametric Augmentation for Time Series Contrastive Learning
https://github.com/AtmaHou/Seq2SeqDataAugmentationForLU
공식 코드Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding
https://github.com/Att100/CP2M
공식 코드CP2M: Clustered-Patch-Mixed Mosaic Augmentation for Aerial Image Segmentation
https://github.com/Audio-WestlakeU/RCT-Random-Consistency-Training
공식 코드RCT: Random Consistency Training for Semi-supervised Sound Event Detection
https://github.com/Avmb/code-docstring-corpus
공식 코드https://github.com/AzulEye/CNN-Failures
공식 코드Why do deep convolutional networks generalize so poorly to small image transformations?
https://github.com/BBillot/SynthSeg
공식 코드SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining
https://github.com/BDBC-KG-NLP/AAAI2023_AWD
공식 코드Adversarial Word Dilution as Text Data Augmentation in Low-Resource Regime
https://github.com/BIT-DA/MetaSAug
공식 코드MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
https://github.com/BITHLP/DRDA
공식 코드Deterministic Reversible Data Augmentation for Neural Machine Translation
https://github.com/BMIRDS/HistoGAN
공식 코드Generative Image Translation for Data Augmentation in Colorectal Histopathology Images
https://github.com/BPYap/BERT-WSD
공식 코드Adapting BERT for Word Sense Disambiguation with Gloss Selection Objective and Example Sentences
https://github.com/BTajini/augfmri
공식 코드Functional Magnetic Resonance Imaging data augmentation through conditional ICA
https://github.com/BUTSpeechFIT/BrnoLM
공식 코드Text Augmentation for Language Models in High Error Recognition Scenario
https://github.com/BaoWangMath/DNN-DataDependentActivation
공식 코드Adversarial Defense via Data Dependent Activation Function and Total Variation Minimization
https://github.com/BaratiLab/AugLiChem
공식 코드AugLiChem: Data Augmentation Library of Chemical Structures for Machine Learning
https://github.com/Becklishious/NeurIPS2024
공식 코드Generative Modeling and Data Augmentation for Power System Production Simulation
https://github.com/BerkeleyAutomation/Kit-Net
공식 코드Kit-Net: Self-Supervised Learning to Kit Novel 3D Objects into Novel 3D Cavities
https://github.com/BestJuly/Pretext-Contrastive-Learning
공식 코드Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation Leaning
https://github.com/Binyr/ASDA
공식 코드Adversarial Semantic Data Augmentation for Human Pose Estimation
https://github.com/BirdVox/birdvoxdetect
공식 코드https://github.com/BirkTorpmannHagen/SegmentationConsistencyTraining
공식 코드Segmentation Consistency Training: Out-of-Distribution Generalization for Medical Image Segmentation
https://github.com/BohanLi0110/NLP-DA-Papers
공식 코드Data Augmentation Approaches in Natural Language Processing: A Survey
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.