# Better Aggregation in Test-Time Augmentation

arXiv: https://arxiv.org/abs/2011.11156 · HTML: https://mlsanity.com/paper/2011.11156/

## Key facts

- Cited by 122 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2020.

## Built on by (most cited first, 30 of 122)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation](https://mlsanity.com/paper/2401.13560/) (2024)
- [Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning](https://mlsanity.com/paper/2308.06038/) (2023)
- [POCO: Point Convolution for Surface Reconstruction](https://mlsanity.com/paper/2201.01831/) (2022)
- [The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech](https://mlsanity.com/paper/2409.09305/) (2024)
- [VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation](https://mlsanity.com/paper/2411.11919/) (2024)
- [Transformation-Equivariant 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/2211.11962/) (2022)
- [Semi-supervised 3D Object Detection with Proficient Teachers](https://mlsanity.com/paper/2207.12655/) (2022)
- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [Frustratingly Easy Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2405.18330/) (2024)
- [ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification](https://mlsanity.com/paper/2304.05538/) (2023)
- [GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation](https://mlsanity.com/paper/2310.00800/) (2023)
- [A Comprehensive Survey on Evidential Deep Learning and Its Applications](https://mlsanity.com/paper/2409.04720/) (2024)
- [A Survey on the Robustness of Computer Vision Models against Common Corruptions](https://mlsanity.com/paper/2305.06024/) (2023)
- [MVDG: A Unified Multi-view Framework for Domain Generalization](https://mlsanity.com/paper/2112.12329/) (2021)
- [Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2303.10457/) (2023)
- [Tyche: Stochastic In-Context Learning for Medical Image Segmentation](https://mlsanity.com/paper/2401.13650/) (2024)
- [The 8th AI City Challenge](https://mlsanity.com/paper/2404.09432/) (2024)
- [Learning Instance-Specific Augmentations by Capturing Local Invariances](https://mlsanity.com/paper/2206.00051/) (2022)
- [MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object Detection](https://mlsanity.com/paper/2212.00442/) (2022)
- [Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models](https://mlsanity.com/paper/2312.15297/) (2023)
- [TIM: A Time Interval Machine for Audio-Visual Action Recognition](https://mlsanity.com/paper/2404.05559/) (2024)
- [Test-Time Distribution Normalization for Contrastively Learned Vision-language Models](https://mlsanity.com/paper/2302.11084/) (2023)
- [STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay](https://mlsanity.com/paper/2407.15773/) (2024)
- [Post-hoc Probabilistic Vision-Language Models](https://mlsanity.com/paper/2412.06014/) (2024)
- [HybridMIM: A Hybrid Masked Image Modeling Framework for 3D Medical Image Segmentation](https://mlsanity.com/paper/2303.10333/) (2023)
- [Exploring Train and Test-Time Augmentations for Audio-Language Learning](https://mlsanity.com/paper/2210.17143/) (2022)
- [Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient](https://mlsanity.com/paper/2308.05681/) (2023)
- [Regularising for invariance to data augmentation improves supervised learning](https://mlsanity.com/paper/2203.03304/) (2022)
- [Online Continual Learning for Robust Indoor Object Recognition](https://mlsanity.com/paper/2307.09827/) (2023)

## 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.