# Identifying the key components in ResNet-50 for diabetic retinopathy grading from fundus images: a systematic investigation

arXiv: https://arxiv.org/abs/2110.14160 · HTML: https://mlsanity.com/paper/2110.14160/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 68 references that are in the map.
- First posted on arXiv 27 Oct 2021.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [Bag of Tricks for Image Classification with Convolutional Neural Networks](https://mlsanity.com/paper/1812.01187/) (2018)
- [ResNet strikes back: An improved training procedure in timm](https://mlsanity.com/paper/2110.00476/) (2021)
- [Boundary loss for highly unbalanced segmentation](https://mlsanity.com/paper/1812.07032/) (2018)
- [Applications of Deep Learning in Fundus Images: A Review](https://mlsanity.com/paper/2101.09864/) (2021)
- [Balanced-MixUp for Highly Imbalanced Medical Image Classification](https://mlsanity.com/paper/2109.09850/) (2021)
- [Zoom-in-Net: Deep Mining Lesions for Diabetic Retinopathy Detection](https://mlsanity.com/paper/1706.04372/) (2017)
- [Deep image mining for diabetic retinopathy screening](https://mlsanity.com/paper/1610.07086/) (2016)
- [DRvertGRADUATE: uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images](https://mlsanity.com/paper/1910.11777/) (2019)
- [Lesion-based Contrastive Learning for Diabetic Retinopathy Grading from Fundus Images](https://mlsanity.com/paper/2107.08274/) (2021)
- [BSDA-Net: A Boundary Shape and Distance Aware Joint Learning Framework for Segmenting and Classifying OCTA Images](https://mlsanity.com/paper/2107.04823/) (2021)
- [Lesion detection and Grading of Diabetic Retinopathy via Two-stages Deep Convolutional Neural Networks](https://mlsanity.com/paper/1705.00771/) (2017)
- [DR-GAN: Conditional Generative Adversarial Network for Fine-Grained Lesion Synthesis on Diabetic Retinopathy Images](https://mlsanity.com/paper/1912.04670/) (2019)

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

- [Self-Supervised Equivariant Regularization Reconciles Multiple Instance Learning: Joint Referable Diabetic Retinopathy Classification and Lesion Segmentation](https://mlsanity.com/paper/2210.05946/) (2022)
- [SSiT: Saliency-guided Self-supervised Image Transformer for Diabetic Retinopathy Grading](https://mlsanity.com/paper/2210.10969/) (2022)
- [Fine-grained Prompt Tuning: A Parameter and Memory Efficient Transfer Learning Method for High-resolution Medical Image Classification](https://mlsanity.com/paper/2403.07576/) (2024)
- [Boosting Memory Efficiency in Transfer Learning for High-Resolution Medical Image Classification](https://mlsanity.com/paper/2408.02426/) (2024)
- [A ResNet is All You Need? Modeling A Strong Baseline for Detecting Referable Diabetic Retinopathy in Fundus Images](https://mlsanity.com/paper/2210.03180/) (2022)
- [Deep Hypothesis Tests Detect Clinically Relevant Subgroup Shifts in Medical Images](https://mlsanity.com/paper/2303.04862/) (2023)
- [UATTA-ENS: Uncertainty Aware Test Time Augmented Ensemble for PIRC Diabetic Retinopathy Detection](https://mlsanity.com/paper/2211.03148/) (2022)
- [SegImgNet: Segmentation-Guided Dual-Branch Network for Retinal Disease Diagnoses](https://mlsanity.com/paper/2503.00267/) (2025)
- [Effect of Data Augmentation on Conformal Prediction for Diabetic Retinopathy](https://mlsanity.com/paper/2508.14266/) (2025)
- [Beyond Predictive Fairness: Quantifying Attribution Consistency Across Demographic Groups in Diabetic Retinopathy Screening](https://mlsanity.com/paper/2608.18759/) (2026)

## Abstract (arXiv)

Although deep learning based diabetic retinopathy (DR) classification methods typically benefit from well-designed architectures of convolutional neural networks, the training setting also has a non-negligible impact on the prediction performance. The training setting includes various interdependent components, such as objective function, data sampling strategy and data augmentation approach. To identify the key components in a standard deep learning framework (ResNet-50) for DR grading, we systematically analyze the impact of several major components. Extensive experiments are conducted on a publicly-available dataset EyePACS. We demonstrate that (1) the DR grading framework is sensitive to input resolution, objective function, and composition of data augmentation, (2) using mean square error as the loss function can effectively improve the performance with respect to a task-specific evaluation metric, namely the quadratically-weighted Kappa, (3) utilizing eye pairs boosts the performance of DR grading and (4) using data resampling to address the problem of imbalanced data distribution in EyePACS hurts the performance. Based on these observations and an optimal combination of the investigated components, our framework, without any specialized network design, achieves the state-of-the-art result (0.8631 for Kappa) on the EyePACS test set (a total of 42670 fundus images) with only image-level labels. We also examine the proposed training practices on other fundus datasets and other network architectures to evaluate their generalizability. Our codes and pre-trained model are available at https://github.com/YijinHuang/pytorch-classification.