多任务MedMNIST分类的共享骨干网络方法
A Shared-Backbone Approach for Multi-Task MedMNIST Classification
浏览论文内容
中文总结 AI 辅助
本研究提出共享骨干网络方法,通过解决分辨率域偏移和优化正则化,在11个MedMNIST数据集上实现多任务分类,最佳配置达到0.73294的调和平均宏F1分数。
中文摘要 AI 辅助
多任务生物医学分类要求模型能够跨不同模态和类别分布进行泛化。我们使用每任务宏F1分数的调和平均数,研究了11个异构的MedMNIST数据集。我们评估了三种带有任务特定线性头的骨干网络。我们发现了MedMNIST API与评估环境之间存在分辨率域偏移。解决这一不一致性并优化架构特定的正则化显著提升了性能。我们最佳的配置,即带有标签平滑的ConvNeXt-Tiny骨干网络,在Tensor Reloaded:多任务MedMNIST竞赛中取得了0.73294的排行榜调和平均宏F1分数,在官方竞赛阶段结束时排名第六。我们的实现可在以下网址公开获取:this https URL
英文摘要
Multi-task biomedical classification requires models to generalize across disparate modalities and class distributions. We study 11 heterogeneous MedMNIST datasets using the harmonic mean of per-task macro-F1. We evaluate three backbones with task-specific linear heads. We identify a resolution domain shift between the MedMNIST API and evaluation environment. Resolving this inconsistency and optimizing architecture-specific regularization substantially improved performance. Our best configuration, a ConvNeXt-Tiny backbone with label smoothing, achieved a leaderboard harmonic-mean macro-F1 of 0.73294 in the Tensor Reloaded: Multi-Task MedMNIST competition, ranking sixth at the close of the official competition phase. Our implementation is publicly available at: https://github.com/GavrilStefan-Dorian/A-Shared-Backbone-Approach-for-Multi-Task-MedMNIST-Classification
发表机构
- Faculty of Computer Science, Alexandru Ioan Cuza University of Iaşi(亚历山德鲁·约安·库扎雅西大学计算机科学学院)
机构由 AI 辅助整理,请以论文原文为准。