# Hierarchical Knowledge Guided Learning for Real-world Retinal Diseases Recognition

arXiv: https://arxiv.org/abs/2111.08913 · HTML: https://mlsanity.com/paper/2111.08913/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 49 references that are in the map.
- First posted on arXiv 17 Nov 2021.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification](https://mlsanity.com/paper/2001.01536/) (2020)
- [Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax](https://mlsanity.com/paper/2006.10408/) (2020)
- [Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets](https://mlsanity.com/paper/2007.09654/) (2020)
- [Dynamic Curriculum Learning for Imbalanced Data Classification](https://mlsanity.com/paper/1901.06783/) (2019)
- [Applications of Deep Learning in Fundus Images: A Review](https://mlsanity.com/paper/2101.09864/) (2021)
- [Hierarchical Image Classification using Entailment Cone Embeddings](https://mlsanity.com/paper/2004.03459/) (2020)
- [Disc-aware Ensemble Network for Glaucoma Screening from Fundus Image](https://mlsanity.com/paper/1805.07549/) (2018)
- [Class-Balanced Distillation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2104.05279/) (2021)
- [Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition](https://mlsanity.com/paper/2104.11057/) (2021)
- [DRvertGRADUATE: uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images](https://mlsanity.com/paper/1910.11777/) (2019)
- [Automatic detection of rare pathologies in fundus photographs using few-shot learning](https://mlsanity.com/paper/1907.09449/) (2019)
- [Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images](https://mlsanity.com/paper/1706.09634/) (2017)
- [Lesion detection and Grading of Diabetic Retinopathy via Two-stages Deep Convolutional Neural Networks](https://mlsanity.com/paper/1705.00771/) (2017)

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

- [HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding](https://mlsanity.com/paper/2311.14064/) (2023)
- [LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition](https://mlsanity.com/paper/2305.04536/) (2023)
- [Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attention](https://mlsanity.com/paper/2502.13693/) (2025)
- [Delving into Out-of-Distribution Detection with Medical Vision-Language Models](https://mlsanity.com/paper/2503.01020/) (2025)
- [Interpretable Few-Shot Retinal Disease Diagnosis with Concept-Guided Prompting of Vision-Language Models](https://mlsanity.com/paper/2503.02917/) (2025)
- [MONICA: Benchmarking on Long-tailed Medical Image Classification](https://mlsanity.com/paper/2410.02010/) (2024)
- [Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlook](https://mlsanity.com/paper/2512.09315/) (2025)
- [PSScreen: Partially Supervised Multiple Retinal Disease Screening](https://mlsanity.com/paper/2508.10549/) (2025)
- [Masked Latent Transformer with the Random Masking Ratio to Advance the Diagnosis of Dental Fluorosis](https://mlsanity.com/paper/2404.13564/) (2024)
- [PSScreen V2: Partially Supervised Multiple Retinal Disease Screening](https://mlsanity.com/paper/2510.22589/) (2025)

## Abstract (arXiv)

In the real world, medical datasets often exhibit a long-tailed data distribution (i.e., a few classes occupy the majority of the data, while most classes have only a limited number of samples), which results in a challenging long-tailed learning scenario. Some recently published datasets in ophthalmology AI consist of more than 40 kinds of retinal diseases with complex abnormalities and variable morbidity. Nevertheless, more than 30 conditions are rarely seen in global patient cohorts. From a modeling perspective, most deep learning models trained on these datasets may lack the ability to generalize to rare diseases where only a few available samples are presented for training. In addition, there may be more than one disease for the presence of the retina, resulting in a challenging label co-occurrence scenario, also known as textitmulti-label, which can cause problems when some re-sampling strategies are applied during training. To address the above two major challenges, this paper presents a novel method that enables the deep neural network to learn from a long-tailed fundus database for various retinal disease recognition. Firstly, we exploit the prior knowledge in ophthalmology to improve the feature representation using a hierarchy-aware pre-training. Secondly, we adopt an instance-wise class-balanced sampling strategy to address the label co-occurrence issue under the long-tailed medical dataset scenario. Thirdly, we introduce a novel hybrid knowledge distillation to train a less biased representation and classifier. We conducted extensive experiments on four databases, including two public datasets and two in-house databases with more than one million fundus images. The experimental results demonstrate the superiority of our proposed methods with recognition accuracy outperforming the state-of-the-art competitors, especially for these rare diseases.