针对胸部X光罕见病种识别难题，提出高效损失与模型组合方案。
Loss Design and Architecture Selection for Long-Tailed Multi-Label Chest X-Ray Classification
- 采用延迟重加权的LDAM损失提升罕见病识别能力
- ConvNeXt-Large模型在开发集上达0.5220 mAP和0.3765 F1
- 实测表明后训练策略有效，适合临床影像不平衡场景
长尾类别分布对多标签胸部X光（CXR）分类构成重大挑战，其中罕见但临床重要的发现严重缺失。本文在包含约14.3万张图像、30个疾病标签的PadChest数据集基础上，对损失函数、CNN主干架构及后训练策略进行了系统性实证评估。实验表明，带有延迟重加权（LDAM-DRW）的LDAM方法在罕见类别识别上持续优于标准BCE和非对称损失。在所评估架构中，ConvNeXt-Large在开发集上表现最佳，mAP为0.5220，F1为0.3765；分类器再训练与测试时增强进一步提升了排名指标。在官方测试排行榜上，我们的提交获得0.3950 mAP，68支队伍共1528次提交中排名第5。我们对开发集到测试集的表现差距进行了坦诚分析，并讨论了临床影像中处理类别不平衡的实际见解。代码已开源。
原文摘要 · Abstract (English)
Long-tailed class distributions pose a significant challenge for multi-label chest X-ray (CXR) classification, where rare but clinically important findings are severely underrepresented. In this work, we present a systematic empirical evaluation of loss functions, CNN backbone architectures and post-training strategies on the CXR-LT 2026 benchmark, comprising approximately 143K images with 30 disease labels from PadChest. Our experiments demonstrate that LDAM with deferred re-weighting (LDAM-DRW) consistently outperforms standard BCE and asymmetric losses for rare class recognition. Amongst the architectures evaluated, ConvNeXt-Large achieves the best single-model performance with 0.5220 mAP and 0.3765 F1 on our development set, whilst classifier re-training and test-time augmentation further improve ranking metrics. On the official test leaderboard, our submission achieved 0.3950 mAP, ranking 5th amongst all 68 participating teams with total of 1528 submissions. We provide a candid analysis of the development-to-test performance gap and discuss practical insights for handling class imbalance in clinical imaging settings. Code is available at https://github.com/Nikhil-Rao20/Long_Tail.
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。