DEEPOREDNET: Contrastive Learning-Based Attention-Weighted Dual Channel Residual Network for Ocular Redness Assessment

Shaopan Wang; Jiezhou He; Xin He; Jiaoyue Hu; Zuguo Liu; Zhiming Luo

ICASSP 2024accepted0 citations

DEEPOREDNET: Contrastive Learning-Based Attention-Weighted Dual Channel Residual Network for Ocular Redness Assessment

Shaopan Wang, Jiezhou He, Xin He, Jiaoyue Hu, Zuguo Liu, Zhiming Luo

Abstract

Ocular redness is highly prevalent worldwide and often accompanied by pain, discomfort, and vision problems, making it an essential signal for monitoring disease development and prognosis. Understanding the category of ocular redness is crucial for health. However, the intricate vascular structure of the ocular surface poses challenges in extracting meaningful features through conventional methods. Moreover, the subtle variations in the signs contribute to the difficulty in achieving accurate discrimination. In this paper, we propose a novel approach named contrastive learning-based attention-weighted dual channel residual network (DeepORedNet) to address the challenging problem. The effectiveness of the proposed network architecture has been validated through detailed experiments. Our proposed DeepORedNet achieves superior performance compared to the baseline models across all evaluation metrics. We hope the proposed framework can effectively facilitate the clinic assessment of ocular redness.

BibTeX

@inproceedings{icassp2024_deeporednetcontr,
  title = {DEEPOREDNET: Contrastive Learning-Based Attention-Weighted Dual Channel Residual Network for Ocular Redness Assessment},
  author = {Shaopan Wang and Jiezhou He and Xin He and Jiaoyue Hu and Zuguo Liu and Zhiming Luo},
  booktitle = {ICASSP 2024},
  year = {2024}
}