面向语义分割自适应数据增强的难度感知样本分配
Difficulty-Aware Sample Allocation for Adaptive Data Augmentation in Semantic Segmentation
- Olabisi Onabanjo University（奥拉比西·奥纳班乔大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出与架构无关的难度感知样本分配（DASA）框架，整合多因素难度信号为样本分配自适应数据增强，在Oxford-IIIT Pet等数据集上提升了U-Net等模型的语义分割性能。
AI中文摘要：
数据增强是现代语义分割流程的标准组成部分，但大多数增强技术要么对训练样本均匀应用变换，要么仅适配损失这类单一难度信号，忽略了分割难度是多因素的事实——模糊预测、持续优化误差、稀有类别、复杂目标边界都会使样本以不同方式具备信息价值。本文提出难度感知样本分配（DASA），这是一种与架构无关的框架，会为被估计为更难的样本分配更强的增强。DASA将预测模糊性、训练损失、类别稀有度、边界复杂度整合为归一化难度分数，在迭代训练期间将该分数映射到样本特定的增强强度。在Oxford-IIIT Pet和二值Pascal VOC分割数据集上，使用U-Net、DeepLabV3、SegFormer-B0开展的实验显示，DASA优于标准训练，且与单一信号自适应基线方法相当或更强；在Oxford-IIIT Pet上，DASA将DeepLabV3的mIoU从0.633提升至0.740；在二值Pascal VOC上，DASA为所有三种评估架构都取得了最佳前景IoU。这些结果证明，多因素难度估计作为一种将增强引导至最有用场景的实用机制具有重要价值。
英文摘要：
Data augmentation is a standard component of modern semantic segmentation pipelines, but most augmentation techniques allocate transformations uniformly across training samples or adapt to a single difficulty signal such as loss. This ignores the fact that segmentation difficulty is multi-factorial, since ambiguous predictions, persistent optimization errors, rare classes, and complex object boundaries can each make a sample informative in different ways. This paper introduces Difficulty-Aware Sample Allocation (DASA), an architecture-agnostic framework that assigns stronger augmentation to samples estimated to be more difficult. DASA combines prediction ambiguity, training loss, class rarity, and boundary complexity into a normalized difficulty score, then maps that score to sample-specific augmentation strength during iterative training. Experiments on Oxford-IIIT Pet and binary Pascal VOC segmentation with U-Net, DeepLabV3, and SegFormer-B0 show that DASA improves over standard training and is competitive with or stronger than single-signal adaptive baselines. On Oxford-IIIT Pet, DASA improves DeepLabV3 from 0.633 to 0.740 mIoU. On binary Pascal VOC, DASA obtains the best foreground IoU for all three evaluated architectures. These results attest to the value of multi-factor difficulty estimation as a practical mechanism for directing augmentation where it is most useful.
