针对像素级长尾分割，提出AUC优化新方法，解决内存与耦合难题。
AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation
- 设计像素级AUC损失函数，建模图像内与图像间复杂依赖关系。
- 引入记忆库缓解大批次内存开销，支持高效训练。
- 在多个基准上验证有效，适合长尾分布下的精细分割任务。
区域受试者工作特征曲线下面积（AUC）是评估实例级长尾学习问题的经典指标。过去二十年中，众多AUC优化方法被提出以提升模型在长尾分布下的性能。本文首次探索像素级长尾语义分割中的AUC优化，该任务面临两大挑战：一方面，像素级任务中AUC优化涉及损失项间的复杂耦合，存在结构化图像内及成对图像间依赖，导致理论分析困难；另一方面，此类任务的AUC损失小批量估计需更大批次，带来不可接受的空间复杂度。为此，我们提出一种像素级AUC损失函数，并基于依赖图进行算法泛化能力的理论分析；同时设计了尾部类别记忆库（T-Memory Bank）以应对显著的内存需求。大量实验在多个基准上验证了AUCSeg的有效性。代码已公开于https://github.com/boyuh/AUCSeg。
原文摘要 · Abstract (English)
The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://github.com/boyuh/AUCSeg.
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。