提出新型门控变换器聚合器，解决医学图像多实例学习注意力集中问题。
QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imaging
- 设计门控变换器架构，通过归一化与注意力门控稳定注意力分布。
- 在六个医学影像基准上平均提升6.1点宏F1，优于现有主流方法。
- 适用于病理切片与细胞级血液学等多种场景，跨域性能稳定。
基于注意力的多实例学习聚合器在医学影像中易出现注意力过度集中，导致预测过自信且不稳定。本文提出QG-MIL，一种门控变换器聚合器，包含四个协同设计组件：基于RMSNorm的预归一化、每头的QK归一化、细粒度注意力输出门控以及SwiGLU风格前馈模块。这些设计共同实现了训练稳定性和实例间注意力分布的均匀性，无需辅助损失、掩码或分阶段正则化。我们在覆盖全切片病理和细胞级血检的六个基准上评估QG-MIL，涵盖两种根本不同的MIL尺度。最佳变体在所有六个基准上均超越领先基线，平均提升6.1点宏F1。注意力叠加图与注意力质量分析表明注意力权重更分散。消融实验显示，虽个别组件在特定数据集上可匹敌完整模型，但QG-MIL整体在跨域表现最一致，方差最小。代码已开源，支持可复现性：https://github.com/unica-visual-intelligence-lab/QG-MIL
原文摘要 · Abstract (English)
Attention-based Multiple Instance Learning aggregators in medical imaging are prone to attention concentration, producing overconfident and unstable predictions. We introduce QG-MIL, a gated transformer aggregator that addresses this through four synergistic architectural components: RMSNorm-based pre-normalization, per-head QK normalization, fine-grained attention output gating, and SwiGLU-style feed-forward modules. Together, these design choices stabilize training and distribute attention more uniformly across instances without auxiliary losses, masking, or multi-stage regularization. We evaluate QG-MIL across six benchmarks spanning whole-slide pathology and cell-level hematology, covering two fundamentally different MIL scales. The best-performing QG-MIL variants outperform leading baselines on all six benchmarks, with an average improvement of +6.1 mean macro F1 points. Attention overlays and attention mass analysis confirm more distributed instance weighting. Ablation studies show that while individual components can match the full model on specific datasets, the QG-MIL design provides the most consistent cross-domain performance and tightest variance when compared to selected baselines. We release a configurable implementation to support reproducibility at: https://github.com/unica-visual-intelligence-lab/QG-MIL
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。