mlsanityData to 7 Oct 2026

Understanding Test-Time Augmentation

arXiv 2402.06892 ↗First posted 10 Feb 2024cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

Test-Time Augmentation (TTA) is a very powerful heuristic that takes advantage of data augmentation during testing to produce averaged output. Despite the experimental effectiveness of TTA, there is insufficient discussion of its theoretical aspects. In this paper, we aim to give theoretical guarantees for TTA and clarify its behavior.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 15 of its 34 references that are in the map. First posted on arXiv 10 Feb 2024.

Builds on

15 of 34 references.

References · 15

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  2. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  3. 2017Random Erasing Data Augmentationcited by 1,235
  4. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
  5. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 278
  6. 2019Fast AutoAugmentcited by 243
  7. 2018GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classificationcited by 242
  8. 2018Synthetic Data Augmentation using GAN for Improved Liver Lesion Classificationcited by 136
  9. 2019Faster AutoAugment: Learning Augmentation Strategies using Backpropagationcited by 96
  10. 2020Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentationcited by 61
  11. 2020Learning Loss for Test-Time Augmentationcited by 56
  12. 2018Automatic Brain Tumor Segmentation using Convolutional Neural Networks with Test-Time Augmentationcited by 36
3 more
  1. 2020Improving Auto-Augment via Augmentation-Wise Weight Sharingcited by 28
  2. 2020Why Mixup Improves the Model Performancecited by 6
  3. 2021Adaptive Test-Time Augmentation for Low-Power CPUcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 10; 2026: 9.

23 papers.

Sort:

By area:

  1. 2024Frustratingly Easy Test-Time Adaptation of Vision-Language Modelscited by 36
  2. 2024Intelligent Multi-View Test Time Augmentationcited by 4
  3. 2025CCStereo: Audio-Visual Contextual and Contrastive Learning for Binaural Audio Generationcited by 4
  4. 2024Test-Time Augmentation Meets Variational Bayescited by 3
  5. 2025UASTHN: Uncertainty-Aware Deep Homography Estimation for UAV Satellite-Thermal Geo-localizationcited by 3
  6. 2025How To Make Your Cell Tracker Say "I dunno!"cited by 1
  7. 2025Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidancecited by 1
  8. 2025Test-Time Augmentation for Pose-invariant Face Recognitioncited by 1
  9. 2025Learning from Random Subspace Exploration: Generalized Test-Time Augmentation with Self-supervised Distillationcited by 1
  10. 2025AMAuT: A Flexible and Efficient Multiview Audio Transformer Framework Trained from Scratchcited by 1
  11. 2024Test-Time Augmentation for Traveling Salesperson Problemcited by 0
  12. 2025Higher-Order Asymptotics of Test-Time Adaptation for Batch Normalization Statisticscited by 0
11 more
  1. 2025prNet: Data-Driven Phase Retrieval via Stochastic Refinementcited by 0
  2. 2025AVP-Fusion: Adaptive Multi-Modal Fusion and Contrastive Learning for Two-Stage Antiviral Peptide Identificationcited by 0
  3. 2026AVP-Pro: An Adaptive Multi-Modal Fusion and Contrastive Learning Approach for Comprehensive Two-Stage Antiviral Peptide Identificationcited by 0
  4. 2026IMSAHLO: Integrating Multi-Scale Attention and Hybrid Loss Optimization Framework for Robust Neuronal Brain Cell Segmentationcited by 0
  5. 2026Annotation Free Spacecraft Detection and Segmentation using Vision Language Modelscited by 0
  6. 2026Ctrl-A: Control-Driven Online Data Augmentationcited by 0
  7. 2026Needle in a Haystack: One-Class Representation Learning for Detecting Rare Malignant Cells in Computational Cytologycited by 0
  8. 2026I Can't Believe TTA Is Not Better: When Test-Time Augmentation Hurts Medical Image Classificationcited by 0
  9. 2026A Comprehensive Inference-Time Augmentation Framework in Physiological Signals: Application to PPG-Based AF Detectioncited by 0
  10. 2026Counterfactual Marginalisation: Framework for Evaluating Robustness to Nuisance Variablescited by 0
  11. 2026RootQuantV2: Adapting a Vision Foundation Model for Root-Trait Regression from Minirhizotron Imagerycited by 0