Unsupervised Medical Image Alignment with Curriculum Learning
- URL: http://arxiv.org/abs/2102.10438v1
- Date: Sat, 20 Feb 2021 20:26:01 GMT
- Title: Unsupervised Medical Image Alignment with Curriculum Learning
- Authors: Mihail Burduja, Radu Tudor Ionescu
- Abstract summary: We explore different curriculum learning methods for training convolutional neural networks on the task of deformable pairwise 3D medical image registration.
Our experiments with an underlying state-of-the-art deep learning model show that curriculum learning can lead to superior results compared to conventional training.
- Score: 16.72680081620203
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We explore different curriculum learning methods for training convolutional
neural networks on the task of deformable pairwise 3D medical image
registration. To the best of our knowledge, we are the first to attempt to
improve performance by training medical image registration models using
curriculum learning, starting from an easy training setup in the first training
stages, and gradually increasing the complexity of the setup. On the one hand,
we consider two existing curriculum learning approaches, namely curriculum
dropout and curriculum by smoothing. On the other hand, we propose a novel and
simple strategy to achieve curriculum, namely to use purposely blurred images
at the beginning, then gradually transit to sharper images in the later
training stages. Our experiments with an underlying state-of-the-art deep
learning model show that curriculum learning can lead to superior results
compared to conventional training.
Related papers
- From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modeling [11.634154932876719]
Masked Image Modeling has emerged as a powerful self-supervised learning paradigm for visual representation learning.
We propose a prototype-driven curriculum leagrning framework that structures the learning process to progress from prototypical examples to more complex variations in the dataset.
Our findings suggest that carefully controlling the order of training examples plays a crucial role in self-supervised visual learning.
arXiv Detail & Related papers (2024-11-16T03:21:06Z) - EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training [79.96741042766524]
We reformulate the training curriculum as a soft-selection function.
We show that exposing the contents of natural images can be readily achieved by the intensity of data augmentation.
The resulting method, EfficientTrain++, is simple, general, yet surprisingly effective.
arXiv Detail & Related papers (2024-05-14T17:00:43Z) - See Through the Fog: Curriculum Learning with Progressive Occlusion in
Medical Imaging [15.382184404673389]
Deep learning models often struggle with challenging images where critical features are partially or fully occluded.
We propose a novel curriculum learning-based approach to train deep learning models to handle occluded medical images effectively.
arXiv Detail & Related papers (2023-06-27T15:53:20Z) - Adapt and Align to Improve Zero-Shot Sketch-Based Image Retrieval [85.39613457282107]
Cross-domain nature of sketch-based image retrieval is challenging.
We present an effective Adapt and Align'' approach to address the key challenges.
Inspired by recent advances in image-text foundation models (e.g., CLIP) on zero-shot scenarios, we explicitly align the learned image embedding with a more semantic text embedding to achieve the desired knowledge transfer from seen to unseen classes.
arXiv Detail & Related papers (2023-05-09T03:10:15Z) - Procedural Image Programs for Representation Learning [62.557911005179946]
We propose training with a large dataset of twenty-one thousand programs, each one generating a diverse set of synthetic images.
These programs are short code snippets, which are easy to modify and fast to execute using.
The proposed dataset can be used for both supervised and unsupervised representation learning, and reduces the gap between pre-training with real and procedurally generated images by 38%.
arXiv Detail & Related papers (2022-11-29T17:34:22Z) - EfficientTrain: Exploring Generalized Curriculum Learning for Training
Visual Backbones [80.662250618795]
This paper presents a new curriculum learning approach for the efficient training of visual backbones (e.g., vision Transformers)
As an off-the-shelf method, it reduces the wall-time training cost of a wide variety of popular models by >1.5x on ImageNet-1K/22K without sacrificing accuracy.
arXiv Detail & Related papers (2022-11-17T17:38:55Z) - Curriculum Meta-Learning for Few-shot Classification [1.5039745292757671]
We propose an adaptation of the curriculum training framework, applicable to state-of-the-art meta learning techniques for few-shot classification.
Our experiments with the MAML algorithm on two few-shot image classification tasks show significant gains with the curriculum training framework.
arXiv Detail & Related papers (2021-12-06T10:29:23Z) - Spatial Transformer Networks for Curriculum Learning [6.107943372244105]
We take inspiration from Spatial Transformer Networks (STNs) in order to form an easy-to-hard curriculum.
We perform various experiments on cluttered MNIST and Fashion-MNIST datasets.
arXiv Detail & Related papers (2021-08-22T12:04:55Z) - Domain Generalization on Medical Imaging Classification using Episodic
Training with Task Augmentation [62.49837463676111]
We propose a novel scheme of episodic training with task augmentation on medical imaging classification.
Motivated by the limited number of source domains in real-world medical deployment, we consider the unique task-level overfitting.
arXiv Detail & Related papers (2021-06-13T03:56:59Z) - Curriculum DeepSDF [85.03886488645873]
We design a "shape curriculum" for learning continuous Signed Distance Function (SDF) on shapes, namely Curriculum DeepSDF.
Inspired by how humans learn, Curriculum DeepSDF organizes the learning task in ascending order of difficulty according to the following two criteria: surface accuracy and sample difficulty.
Experimental results show that a carefully-designed curriculum leads to significantly better shape reconstructions with the same training data, training epochs and network architecture as DeepSDF.
arXiv Detail & Related papers (2020-03-19T06:40:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.