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

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

URL: http://arxiv.org/abs/2310.16783v2
Date: Sat, 6 Jan 2024 07:57:00 GMT
Title: S$^3$-TTA: Scale-Style Selection for Test-Time Augmentation in Biomedical Image Segmentation
Authors: Kangxian Xie, Siyu Huang, Sebastian Cajas Ordone, Hanspeter Pfister, Donglai Wei
Abstract summary: This work proposes a new TTA framework, S$3$-TTA, which selects the suitable image scale and style for each test image. On public benchmarks for cell and lung segmentation, S$3$-TTA demonstrates improvements over the prior art by 3.4% and 1.3%, respectively.
Score: 33.69194889400333
License: http://creativecommons.org/licenses/by/4.0/
Abstract: 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.

Related papers

Test-Time Generative Augmentation for Medical Image Segmentation [20.12850876150199]
We propose a novel approach to enhance medical image segmentation during test time. Instead of employing hand-crafted transforms or functions on the input test image, we advocate for the utilization of an advanced domain-fine-tuned generative model (GM) Experiments conducted across three medical image segmentation tasks demonstrate the efficacy and versatility of the proposed TTGA.
arXiv Detail & Related papers (2024-06-25T14:53:01Z)
Single Image Test-Time Adaptation for Segmentation [22.600586011303363]
This work explores adapting segmentation models to a single unlabelled image with no other data available at test-time. In particular, this work focuses on adaptation by optimizing self-supervised losses at test-time. Our additions to the baselines result in a 3.51 and 3.28 % increase over non-adapted baselines.
arXiv Detail & Related papers (2023-09-25T11:31:18Z)
Self-Sampling Meta SAM: Enhancing Few-shot Medical Image Segmentation with Meta-Learning [17.386754270460273]
We present a Self-Sampling Meta SAM framework for few-shot medical image segmentation. The proposed method achieves significant improvements over state-of-the-art methods in few-shot segmentation. In conclusion, we present a novel approach for rapid online adaptation in interactive image segmentation, adapting to a new organ in just 0.83 minutes.
arXiv Detail & Related papers (2023-08-31T05:20:48Z)
DLTTA: Dynamic Learning Rate for Test-time Adaptation on Cross-domain Medical Images [56.72015587067494]
We propose a novel dynamic learning rate adjustment method for test-time adaptation, called DLTTA. Our method achieves effective and fast test-time adaptation with consistent performance improvement over current state-of-the-art test-time adaptation methods.
arXiv Detail & Related papers (2022-05-27T02:34:32Z)
Automatic size and pose homogenization with spatial transformer network to improve and accelerate pediatric segmentation [51.916106055115755]
We propose a new CNN architecture that is pose and scale invariant thanks to the use of Spatial Transformer Network (STN) Our architecture is composed of three sequential modules that are estimated together during training. We test the proposed method in kidney and renal tumor segmentation on abdominal pediatric CT scanners.
arXiv Detail & Related papers (2021-07-06T14:50:03Z)
MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption [69.76837484008033]
An unresolved problem in Deep Learning is the ability of neural networks to cope with domain shifts during test-time. We combine meta-learning, self-supervision and test-time training to learn to adapt to unseen test distributions. Our approach significantly improves the state-of-the-art results on the CIFAR-10-Corrupted image classification benchmark.
arXiv Detail & Related papers (2021-03-30T09:33:38Z)
Generalize Ultrasound Image Segmentation via Instant and Plug & Play Style Transfer [65.71330448991166]
Deep segmentation models generalize to images with unknown appearance. Retraining models leads to high latency and complex pipelines. We propose a novel method for robust segmentation under unknown appearance shifts.
arXiv Detail & Related papers (2021-01-11T05:45:30Z)
Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classification [97.81205777897043]
Recent work has shown that convolutional neural network classifiers overly rely on texture at the expense of shape cues. We make a similar but different distinction between shape and local image cues, on the one hand, and global image statistics, on the other. Our method, called Permuted Adaptive Instance Normalization (pAdaIN), reduces the representation of global statistics in the hidden layers of image classifiers.
arXiv Detail & Related papers (2020-10-09T16:38:38Z)
Anatomical Data Augmentation via Fluid-based Image Registration [23.280420626023755]
We introduce a fluid-based image augmentation method for medical image analysis. In contrast to existing methods, our framework generates meaningful images via a geodesic subspace.
arXiv Detail & Related papers (2020-07-05T21:06:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.