Data to 7 Oct 2026

Better Aggregation in Test-Time Augmentation

arXiv 2011.11156 ↗First posted 23 Nov 2020cs.CVcited by 121

Not on the map. Why?

Abstract (arXiv)

Test-time augmentation -- the aggregation of predictions across transformed versions of a test input -- is a common practice in image classification. Traditionally, predictions are combined using a simple average. In this paper, we present 1) experimental analyses that shed light on cases in which the simple average is suboptimal and 2) a method to address these shortcomings. A key finding is that even when test-time augmentation produces a net improvement in accuracy, it can change many correct predictions into incorrect predictions. We delve into when and why test-time augmentation changes a prediction from being correct to incorrect and vice versa. Building on these insights, we present a learning-based method for aggregating test-time augmentations. Experiments across a diverse set of models, datasets, and augmentations show that our method delivers consistent improvements over existing approaches.

Key facts. Cited by 121 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 15; 2023: 22; 2024: 31; 2025: 21; 2026: 30.

121 papers.

Sort:

By area:

2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
2024SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentationcited by 266
2023Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuningcited by 150
2022POCO: Point Convolution for Surface Reconstructioncited by 91
2024The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speechcited by 78
2024VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimationcited by 71
2022Transformation-Equivariant 3D Object Detection for Autonomous Drivingcited by 52
2022Semi-supervised 3D Object Detection with Proficient Teacherscited by 45
2023In Search of Lost Online Test-time Adaptation: A Surveycited by 43
2024Frustratingly Easy Test-Time Adaptation of Vision-Language Modelscited by 36
2023ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classificationcited by 33
2023GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentationcited by 29

38 more

2024A Comprehensive Survey on Evidential Deep Learning and Its Applicationscited by 25
2021MVDG: A Unified Multi-view Framework for Domain Generalizationcited by 20
2023Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentationcited by 20
2023A Survey on the Robustness of Computer Vision Models against Common Corruptionscited by 20
2024Tyche: Stochastic In-Context Learning for Medical Image Segmentationcited by 20
2022Learning Instance-Specific Augmentations by Capturing Local Invariancescited by 15
2022MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object Detectioncited by 15
2023Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Modelscited by 15
2024TIM: A Time Interval Machine for Audio-Visual Action Recognitioncited by 15
2024The 8th AI City Challengecited by 15
2023Test-Time Distribution Normalization for Contrastively Learned Vision-language Modelscited by 14
2024STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replaycited by 13
2024Post-hoc Probabilistic Vision-Language Modelscited by 13
2023HybridMIM: A Hybrid Masked Image Modeling Framework for 3D Medical Image Segmentationcited by 12
2022Exploring Train and Test-Time Augmentations for Audio-Language Learningcited by 11
2023Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradientcited by 10
2022Regularising for invariance to data augmentation improves supervised learningcited by 9
2023Online Continual Learning for Robust Indoor Object Recognitioncited by 9
2024Harnessing Uncertainty-aware Bounding Boxes for Unsupervised 3D Object Detectioncited by 9
2024Diversity-Rewarded CFG Distillationcited by 9
2024RFBoost: Understanding and Boosting Deep WiFi Sensing via Physical Data Augmentationcited by 9
2022An Analysis on Ensemble Learning optimized Medical Image Classification with Deep Convolutional Neural Networkscited by 8
2024Improving Black-box Robustness with In-Context Rewritingcited by 8
2024Biophysics Informed Pathological Regularisation for Brain Tumour Segmentationcited by 7
2022Improved Text Classification via Test-Time Augmentationcited by 6
2022Addressing Heterogeneity in Federated Learning via Distributional Transformationcited by 6
2023Approaching Test Time Augmentation in the Context of Uncertainty Calibration for Deep Neural Networkscited by 6
2022Understanding the Tricks of Deep Learning in Medical Image Segmentation: Challenges and Future Directionscited by 5
2023Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language Modelscited by 5
2024BayTTA: Uncertainty-aware medical image classification with optimized test-time augmentation using Bayesian model averagingcited by 5
2022Towards efficient feature sharing in MIMO architecturescited by 4
2022Addressing Distribution Shift at Test Time in Pre-trained Language Modelscited by 4
2022Dynamic Test-Time Augmentation via Differentiable Functionscited by 4
2023Benchmarking Scalable Epistemic Uncertainty Quantification in Organ Segmentationcited by 4
2024Intelligent Multi-View Test Time Augmentationcited by 4
2025CCStereo: Audio-Visual Contextual and Contrastive Learning for Binaural Audio Generationcited by 4
2025Implicit Counterfactual Learning for Audio-Visual Segmentationcited by 4
2025Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantificationcited by 4

50 most cited of 121 All 121 (JSON)