基于视觉变换器的胶囊内镜视频罕见病检测
RARE disease detection from Capsule Endoscopic Videos based on Vision Transformers
- Department of Computer Science, Middlesex University, London, UK（Middlesex大学计算机科学系，伦敦，英国）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文基于视觉变换器改进网络，用于多标签分类任务，实现17种罕见病的检测，测试集mAP@0.5为0.0205，mAP@0.95为0.0196。
AI中文摘要：
本工作对应于胃部竞赛中的多标签分类任务，使用基于Transformer的深度学习网络进行微调。采用Google Vision Transformer (ViT) batch16，分辨率为224x224。总共分类17个标签，包括口腔、食管、胃、小肠、结肠、Z线、幽门、回肠阀、活动性出血、血管扩张、血、侵蚀、红斑、血红素、淋巴管扩张、息肉和溃疡。对于三个视频的测试数据集，整体mAP@0.5为0.0205，整体mAP@0.95为0.0196。
英文摘要：
This work is corresponding to the Gastro Competition for multi-label classification from capsule endoscopic videos (CEV). Deep learning network based on Transformers are fined-tune for this task. The based online mode is Google Vision Transformer (ViT) batch16 with 224 x 224 resolutions. In total, 17 labels are classified, which are mouth, esophagus, stomach, small intestine, colon, z-line, pylorus, ileocecal valve, active bleeding, angiectasia, blood, erosion, erythema, hematin, lymphangioectasis, polyp, and ulcer. For test dataset of three videos, the overall mAP @0.5 is 0.0205 whereas the overall mAP @0.95 is 0.0196.
