S$^3$-TTA: Scale-Style Selection for Test-Time Augmentation in Biomedical Image Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Kangxian, Huang, Siyu, Ordonez, Sebastian Andres Cajas, Pfister, Hanspeter, Wei, Donglai
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913246252892160
author Xie, Kangxian
Huang, Siyu
Ordonez, Sebastian Andres Cajas
Pfister, Hanspeter
Wei, Donglai
author_facet Xie, Kangxian
Huang, Siyu
Ordonez, Sebastian Andres Cajas
Pfister, Hanspeter
Wei, Donglai
contents 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, S$^3$-TTA, which selects the suitable image scale and style for each test image based on a transformation consistency metric. In addition, S$^3$-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, S$^3$-TTA demonstrates improvements over the prior art by 3.4% and 1.3%, respectively, by simply augmenting the input data in testing phase.
format Preprint
id arxiv_https___arxiv_org_abs_2310_16783
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle S$^3$-TTA: Scale-Style Selection for Test-Time Augmentation in Biomedical Image Segmentation
Xie, Kangxian
Huang, Siyu
Ordonez, Sebastian Andres Cajas
Pfister, Hanspeter
Wei, Donglai
Computer Vision and Pattern Recognition
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, S$^3$-TTA, which selects the suitable image scale and style for each test image based on a transformation consistency metric. In addition, S$^3$-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, S$^3$-TTA demonstrates improvements over the prior art by 3.4% and 1.3%, respectively, by simply augmenting the input data in testing phase.
title S$^3$-TTA: Scale-Style Selection for Test-Time Augmentation in Biomedical Image Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2310.16783