GALAR-TemporalNet v2: 基于解剖引导的双分支时间分类方法，结合双向Mamba和双图GCN用于视频胶囊内镜
GALAR-TemporalNet v2: Anatomy-Guided Dual-Branch Temporal Classification with Bidirectional Mamba and Dual-Graph GCN for Video Capsule Endoscopy -- after competition results
AI总结：
该研究针对视频胶囊内镜中同时定位8个解剖区域和检测9种病理发现的多标签时间分类问题，提出GALAR-TemporalNet v2模型，通过结合窗口自注意力、双图GCN和双向Mamba解决类别不平衡、长程时间依赖和病理-解剖纠缠问题，最终在RARE-VISION测试集上取得更高的mAP指标。
摘要：
视频胶囊内镜（VCE）提出了具有挑战性的多标签时间分类问题，要求在数万帧中同时定位8个解剖区域并检测9种病理发现。我们提出了GALAR-TemporalNet v2，一种分层时间模型，旨在解决三个核心挑战：极端类别不平衡、长程时间依赖性和病理-解剖纠缠。我们的架构结合了窗口自注意力进行局部建模，双图GCN用于全局帧关系，以及双向Mamba用于选择性边界上下文编码。新颖的解剖原型残差路径将病理偏差信号与正常器官外观分离，帧级GCN跳跃连接稳定了视觉上易混淆的稀有类别的训练。竞赛版本的GALAR-TemporalNet在RARE-VISION测试集上实现了整体mAP@0.5为0.2644和mAP@0.95为0.2353。在竞赛后，重新设计的GALAR-TemporalNet v2，结合了重构的病理分支、优化的损失函数和扩展的后处理，将这些结果提升到mAP@0.5为0.3409和mAP@0.95为0.3333。
英文摘要：
Video Capsule Endoscopy (VCE) poses a challenging multi-label temporal classification problem, requiring simultaneous localization of 8 anatomical regions and detection of 9 pathological findings across tens of thousands of frames. We present GALAR-TemporalNet v2, a hierarchical temporal model that addresses three core challenges: extreme class imbalance, long-range temporal dependencies, and pathology--anatomy entanglement. Our architecture combines windowed self-attention for local modeling, a Dual-Graph GCN for global frame relationships, and Bidirectional Mamba for selective boundary context encoding. A novel anatomy prototype residual pathway decouples pathological deviation signals from normal organ appearance, and a frame-level GCN skip connection stabilizes training of visually confusable rare classes. The competition version, GALAR-TemporalNet, achieved an overall mAP@0.5 of 0.2644 and mAP@0.95 of 0.2353 on the RARE-VISION test set. Following the competition, the redesigned GALAR-TemporalNet v2 -- incorporating a restructured pathology branch, refined loss functions, and extended post-processing -- improved these results to mAP@0.5 of 0.3409 and mAP@0.95 of 0.3333.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
