mlsanityData to 14 Oct 2026

Learning Loss for Test-Time Augmentation

arXiv 2010.11422 ↗First posted 22 Oct 2020cs.CV cs.AI cs.LGcited by 56

Not on the map. Why?

Abstract (arXiv)

Data augmentation has been actively studied for robust neural networks. Most of the recent data augmentation methods focus on augmenting datasets during the training phase. At the testing phase, simple transformations are still widely used for test-time augmentation. This paper proposes a novel instance-level test-time augmentation that efficiently selects suitable transformations for a test input. Our proposed method involves an auxiliary module to predict the loss of each possible transformation given the input. Then, the transformations having lower predicted losses are applied to the input. The network obtains the results by averaging the prediction results of augmented inputs. Experimental results on several image classification benchmarks show that the proposed instance-aware test-time augmentation improves the model's robustness against various corruptions.

Key facts. Cited by 56 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 7; 2023: 13; 2024: 13; 2025: 9; 2026: 6.

56 papers.

Sort:

By area:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  2. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  3. 2021Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognitioncited by 95
  4. 2024LUQ: Long-text Uncertainty Quantification for LLMscited by 81
  5. 2024VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimationcited by 73
  6. 2023ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classificationcited by 33
  7. 2023GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentationcited by 31
  8. 2021Enhancing Adversarial Robustness via Test-time Transformation Ensemblingcited by 27
  9. 2021Robustness via Cross-Domain Ensemblescited by 23
  10. 2024Understanding Test-Time Augmentationcited by 23
  11. 2023A Survey on the Robustness of Computer Vision Models against Common Corruptionscited by 21
  12. 2021MVDG: A Unified Multi-view Framework for Domain Generalizationcited by 20
38 more
  1. 2024Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classificationcited by 18
  2. 2022Learning Instance-Specific Augmentations by Capturing Local Invariancescited by 15
  3. 2023Test-Time Distribution Normalization for Contrastively Learned Vision-language Modelscited by 14
  4. 2022Exploring Train and Test-Time Augmentations for Audio-Language Learningcited by 11
  5. 2023SwinFSR: Stereo Image Super-Resolution using SwinIR and Frequency Domain Knowledgecited by 10
  6. 2022Regularising for invariance to data augmentation improves supervised learningcited by 9
  7. 2023Online Continual Learning for Robust Indoor Object Recognitioncited by 9
  8. 2024Improving Black-box Robustness with In-Context Rewritingcited by 8
  9. 2021Hierarchical Attention-based Age Estimation and Bias Estimationcited by 7
  10. 2023DC4L: Distribution Shift Recovery via Data-Driven Control for Deep Learning Modelscited by 7
  11. 2023Approaching Test Time Augmentation in the Context of Uncertainty Calibration for Deep Neural Networkscited by 7
  12. 2021Mean Embeddings with Test-Time Data Augmentation for Ensembling of Representationscited by 6
  13. 2022How to Fine-tune Models with Few Samples: Update, Data Augmentation, and Test-time Augmentationcited by 6
  14. 2022Synergy with Translation Artifacts for Training and Inference in Multilingual Taskscited by 6
  15. 2022Addressing Heterogeneity in Federated Learning via Distributional Transformationcited by 6
  16. 2024BayTTA: Uncertainty-aware medical image classification with optimized test-time augmentation using Bayesian model averagingcited by 5
  17. 2022Dynamic Test-Time Augmentation via Differentiable Functionscited by 4
  18. 2023Test-Time Augmentation for 3D Point Cloud Classification and Segmentationcited by 4
  19. 2024Intelligent Multi-View Test Time Augmentationcited by 4
  20. 2025UASTHN: Uncertainty-Aware Deep Homography Estimation for UAV Satellite-Thermal Geo-localizationcited by 4
  21. 2023Joint Optimization of Class-Specific Training- and Test-Time Data Augmentation in Segmentationcited by 3
  22. 2024Towards detecting unanticipated bias in Large Language Modelscited by 3
  23. 2024Test-Time Augmentation Meets Variational Bayescited by 3
  24. 2025Hummingbird: High Fidelity Image Generation via Multimodal Context Alignmentcited by 3
  25. 2025Test-time augmentation improves efficiency in conformal predictioncited by 3
  26. 2021Adaptive Test-Time Augmentation for Low-Power CPUcited by 2
  27. 2023Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applicationscited by 2
  28. 2023Delay-SDE-net: A deep learning approach for time series modelling with memory and uncertainty estimatescited by 2
  29. 2024Test-time Adaptation Meets Image Enhancement: Improving Accuracy via Uncertainty-aware Logit Switchingcited by 2
  30. 2026Inverting Data Transformations via Diffusion Samplingcited by 2
  31. 2024Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-Timecited by 1
  32. 2025Test-Time Augmentation for Pose-invariant Face Recognitioncited by 1
  33. 2025Learning from Random Subspace Exploration: Generalized Test-Time Augmentation with Self-supervised Distillationcited by 1
  34. 2025Probabilistic Hyper-Graphs using Multiple Randomly Masked Autoencoders for Semi-supervised Multi-modal Multi-task Learningcited by 1
  35. 2025Does Homophily Help in Robust Test-time Node Classification?cited by 1
  36. 2024Test-Time Augmentation for Traveling Salesperson Problemcited by 0
  37. 2024Just rotate it! Uncertainty estimation in closed-source models via multiple queriescited by 0
  38. 2025Cumulative Consensus Score: Label-Free and Model-Agnostic Evaluation of Object Detectors in Deploymentcited by 0

50 most cited of 56 All 56 (JSON)