AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation
Han, Boyu, Xu, Qianqian, Yang, Zhiyong, Bao, Shilong, Wen, Peisong, Jiang, Yangbangyan, Huang, Qingming
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Oct-10-2024
- Country:
- Asia (0.14)
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (1.00)
- Research Report
- Industry:
- Health & Medicine > Therapeutic Area (0.45)
- Leisure & Entertainment > Sports (0.45)
- Transportation > Ground
- Road (0.46)
- Technology: