FP4量化下，模型架构比训练配方更重要，Swin Transformer最抗干扰。
Not All NVFP4 QAT Recipes Are Equal: How Architecture and Scale Shape Model Quality for Anomaly Segmentation
- 对比不同架构、规模与量化配方的三重影响
- 注意力架构在大模型下更抗量化噪声，CNN易退化
- Swin Transformer适配所有配方，适合低精度异常分割
实时异常分割需兼顾高召回率与低精度高效推理。我们在脑肿瘤分割这一召回关键任务中，系统研究了模型架构、模型规模与FP4量化感知训练（QAT）配方三者之间的相互作用，采用统一协议评估多种架构、规模与QAT配方。结果表明，架构选择对量化鲁棒性影响最大：基于注意力的架构对配方变化具有显著韧性，而卷积网络在大规模下使用梯度量化配方时性能下降明显。小规模下FP4可离散化softmax注意力，但先进QAT配方能防止其崩溃；大规模下，先进配方可缓解梯度量化噪声导致的CNN性能下降。五折患者级交叉验证确认结果对数据划分稳健。研究表明，Swin Transformer在所有规模下均对QAT配方不敏感，是FP4量化异常分割的推荐架构。
原文摘要 · Abstract (English)
Real-time anomaly segmentation demands both high recall and efficient low-precision inference. We study the three-way interaction of model architecture, model scale, and FP4 quantization-aware training (QAT) recipe on a recall-critical brain tumor segmentation task, evaluating multiple architectures, scales, and QAT recipes under a unified protocol. We find that architecture choice has the largest impact on quantization robustness, with attention-based architectures showing remarkable resilience to recipe choice while CNN degrades under gradient-quantizing recipes at larger scales. At low capacity, FP4 can discretize softmax attention, but advanced QAT recipes prevent this collapse. At larger scales, advanced recipes mitigate gradient quantization noise that degrades CNN quality. Five-fold patient-level cross-validation confirms these findings are robust to data partition. Our results show that the Swin Transformer is robust to QAT recipe choice across all scales, making it the recommended architecture for FP4-quantized anomaly segmentation.
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。