针对胃肠道视频分析中罕见病灶识别难问题，改进了ResNet-50模型与时间解码策略。
ResNet-50 with Class Reweighting and Anatomy-Guided Temporal Decoding for Gastrointestinal Video Analysis
- 采用裁剪加权损失缓解17类标签中的严重类别不平衡。
- 通过解码器设计将时间mAP从0.3801提升至0.4303。
- 适合医学影像分析、多标签视频理解方向的研究者参考。
我们构建了一个基于ResNet-50帧分类器的多标签胃肠道视频分析流程，并引入解剖结构引导的时间事件解码。系统从336×336尺寸帧中预测17个标签，包括5个解剖结构类和12个病理类。主要挑战是罕见病理标签的严重类别不平衡。为此，我们在训练损失中使用截断的类别加权正样本权重，提升了稀有类学习能力，同时保持优化稳定。在时间阶段发现，直接帧到事件转换会产生与官方标注碎片化不一致的问题。最终方案结合了类似真值的帧级事件组合、解剖投票平滑以及基于解剖结构的病理门控机制，并采用保守滞后解码器。该设计使测试集上的时间mAP从0.3801提升至0.4303。
原文摘要 · Abstract (English)
We developed a multi-label gastrointestinal video analysis pipeline based on a ResNet-50 frame classifier followed by anatomy-guided temporal event decoding. The system predicts 17 labels, including 5 anatomy classes and 12 pathology classes, from frames resized to 336x336. A major challenge was severe class imbalance, particularly for rare pathology labels. To address this, we used clipped class-wise positive weighting in the training loss, which improved rare-class learning while maintaining stable optimization. At the temporal stage, we found that direct frame-to-event conversion produced fragmented mismatches with the official ground truth. The final submission therefore combined GT-style framewise event composition, anatomy vote smoothing, and anatomy-based pathology gating with a conservative hysteresis decoder. This design improved the final temporal mAP from 0.3801 to 0.4303 on the challenge test set.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。