# Unsupervised Medical Image Alignment with Curriculum Learning

arXiv: https://arxiv.org/abs/2102.10438 · HTML: https://mlsanity.com/paper/2102.10438/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 20 Feb 2021.

## Builds on (most cited first, 13 of 13)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [A large annotated medical image dataset for the development and evaluation of segmentation algorithms](https://mlsanity.com/paper/1902.09063/) (2019)
- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [An Unsupervised Learning Model for Deformable Medical Image Registration](https://mlsanity.com/paper/1802.02604/) (2018)
- [Recursive Cascaded Networks for Unsupervised Medical Image Registration](https://mlsanity.com/paper/1907.12353/) (2019)
- [Unsupervised 3D End-to-End Medical Image Registration with Volume Tweening Network](https://mlsanity.com/paper/1902.05020/) (2019)
- [How hard can it be? Estimating the difficulty of visual search in an image](https://mlsanity.com/paper/1705.08280/) (2017)
- [Curriculum Dropout](https://mlsanity.com/paper/1703.06229/) (2017)

## Built on by (most cited first, 10 of 10)

- [CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for Non-Contrast to Contrast CT Translation](https://mlsanity.com/paper/2110.06400/) (2021)
- [Learning Rate Curriculum](https://mlsanity.com/paper/2205.09180/) (2022)
- [A Psychology-based Unified Dynamic Framework for Curriculum Learning](https://mlsanity.com/paper/2408.05326/) (2024)
- [CBM: Curriculum by Masking](https://mlsanity.com/paper/2407.05193/) (2024)
- [Progressive Curriculum Learning with Scale-Enhanced U-Net for Continuous Airway Segmentation](https://mlsanity.com/paper/2410.18456/) (2024)
- [DCL-SE: Dynamic Curriculum Learning for Spatiotemporal Encoding of Brain Imaging](https://mlsanity.com/paper/2511.15151/) (2025)
- [Deep learning in medical image registration: introduction and survey](https://mlsanity.com/paper/2309.00727/) (2023)
- [CL4KGE: A Curriculum Learning Method for Knowledge Graph Embedding](https://mlsanity.com/paper/2408.14840/) (2024)
- [CLoE: Curriculum Learning on Endoscopic Images for Robust MES Classification](https://mlsanity.com/paper/2508.13280/) (2025)
- [Mimicking Human Visual Development for Learning Robust Image Representations](https://mlsanity.com/paper/2512.14360/) (2025)

## Abstract (arXiv)

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. Additionally, we show that curriculum by input blur has the best accuracy versus speed trade-off among the compared curriculum learning approaches.