# Multi-Scale Multi-Target Domain Adaptation for Angle Closure Classification

arXiv: https://arxiv.org/abs/2208.12157 · HTML: https://mlsanity.com/paper/2208.12157/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 25 Aug 2022.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [Domain Agnostic Learning with Disentangled Representations](https://mlsanity.com/paper/1904.12347/) (2019)
- [One-Sided Unsupervised Domain Mapping](https://mlsanity.com/paper/1706.00826/) (2017)
- [Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation](https://mlsanity.com/paper/1702.07841/) (2017)
- [Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach](https://mlsanity.com/paper/1810.11547/) (2018)
- [AlignedReID: Surpassing Human-Level Performance in Person Re-Identification](https://mlsanity.com/paper/1711.08184/) (2017)
- [Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis](https://mlsanity.com/paper/2007.07222/) (2020)
- [ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.10812/) (2021)
- [Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.10856/) (2022)
- [Adversarial Domain Adaptation for Classification of Prostate Histopathology Whole-Slide Images](https://mlsanity.com/paper/1806.01357/) (2018)
- [AGE Challenge: Angle Closure Glaucoma Evaluation in Anterior Segment Optical Coherence Tomography](https://mlsanity.com/paper/2005.02258/) (2020)
- [Domain-Agnostic Learning with Anatomy-Consistent Embedding for Cross-Modality Liver Segmentation](https://mlsanity.com/paper/1908.10489/) (2019)
- [Multi-Context Deep Network for Angle-Closure Glaucoma Screening in Anterior Segment OCT](https://mlsanity.com/paper/1809.03239/) (2018)

## Abstract (arXiv)

Deep learning (DL) has made significant progress in angle closure classification with anterior segment optical coherence tomography (AS-OCT) images. These AS-OCT images are often acquired by different imaging devices/conditions, which results in a vast change of underlying data distributions (called "data domains"). Moreover, due to practical labeling difficulties, some domains (e.g., devices) may not have any data labels. As a result, deep models trained on one specific domain (e.g., a specific device) are difficult to adapt to and thus may perform poorly on other domains (e.g., other devices). To address this issue, we present a multi-target domain adaptation paradigm to transfer a model trained on one labeled source domain to multiple unlabeled target domains. Specifically, we propose a novel Multi-scale Multi-target Domain Adversarial Network (M2DAN) for angle closure classification. M2DAN conducts multi-domain adversarial learning for extracting domain-invariant features and develops a multi-scale module for capturing local and global information of AS-OCT images. Based on these domain-invariant features at different scales, the deep model trained on the source domain is able to classify angle closure on multiple target domains even without any annotations in these domains. Extensive experiments on a real-world AS-OCT dataset demonstrate the effectiveness of the proposed method.