mlsanityData to 14 Oct 2026

Improved Text Classification via Test-Time Augmentation

arXiv 2206.13607 ↗First posted 27 Jun 2022cs.LG cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models. Importantly, TTA can be used to improve model performance post-hoc, without additional training. Although test-time augmentation (TTA) can be applied to any data modality, it has seen limited adoption in NLP due in part to the difficulty of identifying label-preserving transformations. In this paper, we present augmentation policies that yield significant accuracy improvements with language models. A key finding is that augmentation policy design -- for instance, the number of samples generated from a single, non-deterministic augmentation -- has a considerable impact on the benefit of TTA. Experiments across a binary classification task and dataset show that test-time augmentation can deliver consistent improvements over current state-of-the-art approaches.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 25 of its 34 references that are in the map. First posted on arXiv 27 Jun 2022.

Builds on

25 of 34 references.

References · 25

  1. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  2. 2014Going Deeper with Convolutionscited by 4,241
  3. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  4. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  5. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
  6. 2021A Survey of Data Augmentation Approaches for NLPcited by 409
  7. 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 404
  8. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 280
  9. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
  10. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  11. 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
  12. 2019Good-Enough Compositional Data Augmentationcited by 158
13 more
  1. 2017Data Augmentation for Low-Resource Neural Machine Translationcited by 139
  2. 2020Better Aggregation in Test-Time Augmentationcited by 122
  3. 2016Data Recombination for Neural Semantic Parsingcited by 111
  4. 2020An Analysis of Simple Data Augmentation for Named Entity Recognitioncited by 76
  5. 2018Deflecting Adversarial Attacks with Pixel Deflectioncited by 71
  6. 2019Generalized Data Augmentation for Low-Resource Translationcited by 53
  7. 2019XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answeringcited by 35
  8. 2017Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network Ensemblecited by 23
  9. 2019An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answeringcited by 22
  10. 2019Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answeringcited by 21
  11. 2019Sequence-to-sequence Pre-training with Data Augmentation for Sentence Rewritingcited by 12
  12. 2019Transforming Wikipedia into Augmented Data for Query-Focused Summarizationcited by 12
  13. 2019Controllable Data Synthesis Method for Grammatical Error Correctioncited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 1; 2025: 1; 2026: 2.

7 papers.

  1. 2023Online Continual Learning for Robust Indoor Object Recognitioncited by 9
  2. 2024Improving Black-box Robustness with In-Context Rewritingcited by 8
  3. 2022Addressing Distribution Shift at Test Time in Pre-trained Language Modelscited by 4
  4. 2025Test-time augmentation improves efficiency in conformal predictioncited by 3
  5. 2023UATTA-EB: Uncertainty-Aware Test-Time Augmented Ensemble of BERTs for Classifying Common Mental Illnesses on Social Media Postscited by 0
  6. 2026Test-Time Augmentation for LLMs: When Input Diversity Beats Output Diversity at Matched Computecited by 0
  7. 2026GATTA: Graph Active Learning with Test-Time Augmentationcited by 0