mlsanityData to 7 Oct 2026

Test-Time Mixup Augmentation for Data and Class-Specific Uncertainty Estimation in Deep Learning Image Classification

arXiv 2212.00214 ↗First posted 1 Dec 2022cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Uncertainty estimation of trained deep learning networks is valuable for optimizing learning efficiency and evaluating the reliability of network predictions. In this paper, we propose a method for estimating uncertainty in deep learning image classification using test-time mixup augmentation (TTMA). To improve the ability to distinguish correct and incorrect predictions in existing aleatoric uncertainty, we introduce TTMA data uncertainty (TTMA-DU) by applying mixup augmentation to test data and measuring the entropy of the predicted label histogram. In addition to TTMA-DU, we propose TTMA class-specific uncertainty (TTMA-CSU), which captures aleatoric uncertainty specific to individual classes and provides insight into class confusion and class similarity within the trained network. We validate our proposed methods on the ISIC-18 skin lesion diagnosis dataset and the CIFAR-100 real-world image classification dataset. Our experiments show that (1) TTMA-DU more effectively differentiates correct and incorrect predictions compared to existing uncertainty measures due to mixup perturbation, and (2) TTMA-CSU provides information on class confusion and class similarity for both datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 56 references that are in the map. First posted on arXiv 1 Dec 2022.

Builds on

37 of 56 references.

References · 37

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Wide Residual Networkscited by 3,057
  5. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  6. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  7. 2017Deep Bayesian Active Learning with Image Datacited by 812
  8. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  9. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 657
  10. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  11. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 516
  12. 2020Contrastive learning of global and local features for medical image segmentation with limited annotationscited by 309
25 more
  1. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  2. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 278
  3. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 260
  4. 2020SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularizationcited by 149
  5. 2019Augmenting Data with Mixup for Sentence Classification: An Empirical Studycited by 125
  6. 2018MILD-Net: Minimal Information Loss Dilated Network for Gland Instance Segmentation in Colon Histology Imagescited by 87
  7. 2021Context Decoupling Augmentation for Weakly Supervised Semantic Segmentationcited by 69
  8. 2020ResizeMix: Mixing Data with Preserved Object Information and True Labelscited by 68
  9. 2022Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentationcited by 64
  10. 2020SuperMix: Supervising the Mixing Data Augmentationcited by 58
  11. 2020VideoMix: Rethinking Data Augmentation for Video Classificationcited by 55
  12. 2020Combining Ensembles and Data Augmentation can Harm your Calibrationcited by 44
  13. 2020Structured Consistency Loss for semi-supervised semantic segmentationcited by 39
  14. 2021Is segmentation uncertainty useful?cited by 37
  15. 2020Local Additivity Based Data Augmentation for Semi-supervised NERcited by 31
  16. 2019Overfitting of neural nets under class imbalance: Analysis and improvements for segmentationcited by 27
  17. 2019Improving Robustness of Deep Learning Based Knee MRI Segmentation: Mixup and Adversarial Domain Adaptationcited by 27
  18. 2017Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network Ensemblecited by 23
  19. 2020An Uncertainty-aware Transfer Learning-based Framework for Covid-19 Diagnosiscited by 22
  20. 2019Semi-supervised semantic segmentation needs strong, varied perturbationscited by 14
  21. 2020Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognitioncited by 13
  22. 2020Integrating uncertainty in deep neural networks for MRI based stroke analysiscited by 12
  23. 2020Deep Active Learning with Augmentation-based Consistency Estimationcited by 8
  24. 2020SkiNet: A Deep Learning Solution for Skin Lesion Diagnosis with Uncertainty Estimation and Explainabilitycited by 2
  25. 2021CUAB: Convolutional Uncertainty Attention Block Enhanced the Chest X-ray Image Analysiscited by 2

Built on by

Not cited yet.