SOTAVerified

Data Augmentation

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:

( Image credit: Albumentations )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 5751–5800 of 8378 papers

TitleStatusHype
Semi-supervised transfer learning for language expansion of end-to-end speech recognition models to low-resource languages—0
Toxicity Detection can be Sensitive to the Conversational Context—0
A comparison of streaming models and data augmentation methods for robust speech recognition—0
Self-Supervised Class Incremental Learning—0
FLSys: Toward an Open Ecosystem for Federated Learning Mobile Apps—0
Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification—0
Context-Aware Language Modeling for Goal-Oriented Dialogue Systems—0
Retrieval Data Augmentation Informed by Downstream Question Answering Performance—0
Retrieval-guided Counterfactual Generation for QA—0
TextMosaic: A New Data Augmentation Method for Named Entity Recognition Using Document-Level Contexts—0
Global Mixup: Eliminating Ambiguity with Clustering Relationships—0
SegMix: A Simple Structure-Aware Data Augmentation Method—0
Data Augmentation using Random Image Cropping for High-resolution Virtual Try-On (VITON-CROP)—0
Compositional Data Augmentation for Abstractive Conversation Summarization—0
Data Augmentation and Learned Layer Aggregation for Improved Multilingual Language Understanding in Dialogue—0
TransSGAN: GAN based semi-superivsed learning for text classification with Transformer Encoder—0
Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks—0
An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models—0
EveMRC: A Two-stage Evidence Modeling For Multi-choice Machine Reading Comprehension—0
DAML: Chinese Named Entity Recognition with a fusion method of data-augmentation and meta-learning—0
Learning to Ignore Adversarial Attacks—0
Improving Multimodal Speech Recognition by Data Augmentation and Speech Representations—0
When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation—0
BERT is Robust! A Case Against Synonym-Based Adversarial Examples in Text Classification—0
LINDA: Unsupervised Learning to Interpolate in Natural Language Processing—0
Improving Robustness of Language Models from a Geometry-aware Perspective—0
Vec2Node: Self-training with Tensor Augmentation for Text Classification with Few Labels—0
Single-stage uav detection and classification with yolov5: Mosaic data augmentation and panetCode0
Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text—0
Quantum-inspired Representation for Long-tail Senses of Word Sense Disambiguation—0
Towards Better Citation Intent Classification—0
Data Augmentation for Intent Classification with Generic Large Language Models—0
Explicit Modeling the Context for Chinese NER—0
PESTO: A Post-User Fusion Network for Rumour Detection on Social Media—0
QA Domain Adaptation using Data Augmentation and Contrastive Adaptation—0
NVIDIA NeMo Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21—0
MoRe-Fi: Motion-robust and Fine-grained Respiration Monitoring via Deep-Learning UWB Radar—0
Addressing Resource and Privacy Constraints in Semantic Parsing Through Data Augmentation—0
Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation—0
CST5: Data augmentation for Code-Switched Semantic Parsing—0
DAWSON: Data Augmentation using Weak Supervision On Natural Language—0
Do We Need to Differentiate Negative Candidates Before Training a Neural Ranker?—0
Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation—0
UNICON: Unsupervised Intent Discovery via Semantic-level Contrastive Learning—0
Data Augmentation with Sentence Recombination Method for Semi-supervised Text Classification—0
Contrastive Learning for Low Resource Machine Translation—0
Reinforcement Learning of Self Enhancing Camera Image and Signal ProcessingCode0
Analysis of Data Augmentation Methods for Low-Resource Maltese ASR—0
T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging—0
Evaluating Contrastive Learning on Wearable Timeseries for Downstream Clinical Outcomes—0
Show:102550
← PrevPage 116 of 168Next →
All datasetsImageNetCIFAR-10GA1457

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DeiT-B (+MixPro)Accuracy (%)82.9—Unverified
2ResNet-200 (DeepAA)Accuracy (%)81.32—Unverified
3DeiT-S (+MixPro)Accuracy (%)81.3—Unverified
4ResNet-200 (Fast AA)Accuracy (%)80.6—Unverified
5ResNet-200 (UA)Accuracy (%)80.4—Unverified
6ResNet-200 (AA)Accuracy (%)80—Unverified
7ResNet-50 (DeepAA)Accuracy (%)78.3—Unverified
8ResNet-50 (TA wide)Accuracy (%)78.07—Unverified
9ResNet-50 (LoRot-E)Accuracy (%)77.72—Unverified
10ResNet-50 (LoRot-I)Accuracy (%)77.71—Unverified
#ModelMetricClaimedVerifiedStatus
1WideResNet-40-2 (Faster AA)Percentage error3.7—Unverified
2Shake-Shake (26 2×32d) (Faster AA)Percentage error2.7—Unverified
3WideResNet-28-10 (Faster AA)Percentage error2.6—Unverified
4Shake-Shake (26 2×96d) (Faster AA)Percentage error2—Unverified
5Shake-Shake (26 2×112d) (Faster AA)Percentage error2—Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7—Unverified
2PaCMAPClassification Accuracy85.3—Unverified
3hNNEClassification Accuracy77.4—Unverified
4TopoAEClassification Accuracy74.6—Unverified