Related papers: Stronger is not better: Better Augmentations in Contrastive Learning for Medical Image Segmentation

Stronger is not better: Better Augmentations in Contrastive Learning for Medical Image Segmentation

URL: http://arxiv.org/abs/2512.05992v1
Date: Sun, 30 Nov 2025 22:42:49 GMT
Title: Stronger is not better: Better Augmentations in Contrastive Learning for Medical Image Segmentation
Abstract summary: This paper evaluates strong data augmentation, one of the most important components for self-supervised contrastive learning's improved performance.<n>We find that the existing data augmentations do not always improve performance for semantic segmentation for medical images.
Score: 0.08311645599700011
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Self-supervised contrastive learning is among the recent representation learning methods that have shown performance gains in several downstream tasks including semantic segmentation. This paper evaluates strong data augmentation, one of the most important components for self-supervised contrastive learning's improved performance. Strong data augmentation involves applying the composition of multiple augmentation techniques on images. Surprisingly, we find that the existing data augmentations do not always improve performance for semantic segmentation for medical images. We experiment with other augmentations that provide improved performance.

Related papers

Efficacy of Image Similarity as a Metric for Augmenting Small Dataset Retinal Image Segmentation [0.0]
A common metric for evaluating synthetic image quality is the Fr'echet Inception Distance (FID) which measures the similarity of two image datasets.<n>We show that the behaviour of augmenting with standard and synthetic images agrees with previously conducted experiments.<n>As FID between the training and augmenting datasets decreases, the augmentation datasets are shown to contribute to significant and robust improvements in image segmentation.
arXiv Detail & Related papers (2025-07-07T10:38:45Z)
Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning [7.6834562879925885]
Recent work suggests that good augmentations are label-preserving with respect to a specific downstream task. We show that label-destroying augmentations can be useful in the foundation model setting.
arXiv Detail & Related papers (2022-12-16T10:08:38Z)
Style Augmentation improves Medical Image Segmentation [0.0]
style augmentation, which is already used in classification tasks, helps reducing texture over-fitting and improves segmentation performance. This work shows on the MoNuSeg dataset that style augmentation, which is already used in classification tasks, helps reducing texture over-fitting and improves segmentation performance.
arXiv Detail & Related papers (2022-11-02T14:00:12Z)
MSR: Making Self-supervised learning Robust to Aggressive Augmentations [98.6457801252358]
We propose a new SSL paradigm, which counteracts the impact of semantic shift by balancing the role of weak and aggressively augmented pairs. We show that our model achieves 73.1% top-1 accuracy on ImageNet-1K with ResNet-50 for 200 epochs, which is a 2.5% improvement over BYOL.
arXiv Detail & Related papers (2022-06-04T14:27:29Z)
TeachAugment: Data Augmentation Optimization Using Teacher Knowledge [11.696069523681178]
We propose a data augmentation optimization method based on the adversarial strategy called TeachAugment. We show that TeachAugment outperforms existing methods in experiments of image classification, semantic segmentation, and unsupervised representation learning tasks.
arXiv Detail & Related papers (2022-02-25T06:22:51Z)
Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation [83.31087402305306]
robustness to trimaps and generalization to images from different domains is still under-explored. We propose an image matting method which achieves higher robustness (RMat) via multilevel context assembling and strong data augmentation targeting matting.
arXiv Detail & Related papers (2022-01-18T11:45:17Z)
Residual Relaxation for Multi-view Representation Learning [64.40142301026805]
Multi-view methods learn by aligning multiple views of the same image. Some useful augmentations, such as image rotation, are harmful for multi-view methods because they cause a semantic shift. We develop a generic approach, Pretext-aware Residual Relaxation (Prelax), that relaxes the exact alignment.
arXiv Detail & Related papers (2021-10-28T17:57:17Z)
Contrastive Learning with Stronger Augmentations [63.42057690741711]
We propose a general framework called Contrastive Learning with Stronger Augmentations(A) to complement current contrastive learning approaches. Here, the distribution divergence between the weakly and strongly augmented images over the representation bank is adopted to supervise the retrieval of strongly augmented queries. Experiments showed the information from the strongly augmented images can significantly boost the performance.
arXiv Detail & Related papers (2021-04-15T18:40:04Z)
Synthetic Convolutional Features for Improved Semantic Segmentation [139.5772851285601]
We suggest to generate intermediate convolutional features and propose the first synthesis approach that is catered to such intermediate convolutional features. This allows us to generate new features from label masks and include them successfully into the training procedure. Experimental results and analysis on two challenging datasets Cityscapes and ADE20K show that our generated feature improves performance on segmentation tasks.
arXiv Detail & Related papers (2020-09-18T14:12:50Z)
Image Augmentations for GAN Training [57.65145659417266]
We provide insights and guidelines on how to augment images for both vanilla GANs and GANs with regularizations. Surprisingly, we find that vanilla GANs attain generation quality on par with recent state-of-the-art results.
arXiv Detail & Related papers (2020-06-04T00:16:02Z)

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