# S3-TTA: Scale-Style Selection for Test-Time Augmentation in Biomedical Image Segmentation

arXiv: https://arxiv.org/abs/2310.16783 · HTML: https://mlsanity.com/paper/2310.16783/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 25 Oct 2023.

## Builds on (most cited first, 12 of 12)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [Style Augmentation: Data Augmentation via Style Randomization](https://mlsanity.com/paper/1809.05375/) (2018)
- [Neural Style Transfer Improves 3D Cardiovascular MR Image Segmentation on Inconsistent Data](https://mlsanity.com/paper/1909.09716/) (2019)
- [Random Style Transfer based Domain Generalization Networks Integrating Shape and Spatial Information](https://mlsanity.com/paper/2008.12205/) (2020)
- [CellTranspose: Few-shot Domain Adaptation for Cellular Instance Segmentation](https://mlsanity.com/paper/2212.14121/) (2022)
- [Remove Appearance Shift for Ultrasound Image Segmentation via Fast and Universal Style Transfer](https://mlsanity.com/paper/2002.05844/) (2020)
- [Generalize Ultrasound Image Segmentation via Instant and Plug & Play Style Transfer](https://mlsanity.com/paper/2101.03711/) (2021)
- [Style-invariant Cardiac Image Segmentation with Test-time Augmentation](https://mlsanity.com/paper/2009.12193/) (2020)
- [Instance Segmentation of Unlabeled Modalities via Cyclic Segmentation GAN](https://mlsanity.com/paper/2204.03082/) (2022)

## Abstract (arXiv)

Deep-learning models have been successful in biomedical image segmentation. To generalize for real-world deployment, test-time augmentation (TTA) methods are often used to transform the test image into different versions that are hopefully closer to the training domain. Unfortunately, due to the vast diversity of instance scale and image styles, many augmented test images produce undesirable results, thus lowering the overall performance. This work proposes a new TTA framework, S3-TTA, which selects the suitable image scale and style for each test image based on a transformation consistency metric. In addition, S3-TTA constructs an end-to-end augmentation-segmentation joint-training pipeline to ensure a task-oriented augmentation. On public benchmarks for cell and lung segmentation, S3-TTA demonstrates improvements over the prior art by 3.4% and 1.3%, respectively, by simply augmenting the input data in testing phase.