开放世界环境下面向语义场景理解的公平持续学习方法
Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments
AI总结：
针对持续语义分割中的公平性、灾难性遗忘与背景偏移问题，提出基于类别分布的公平持续学习框架及原型对比聚类和条件结构一致性损失，在三个基准上达到最优性能并提升公平性。
摘要：
持续语义分割旨在学习新类别，同时保留来自先前类别的信息。尽管已有研究近年来展现出令人瞩目的进展，但持续语义分割中的公平性问题仍需得到更好解决。同时，公平性是部署深度学习模型时最重要的因素之一，尤其是在与人相关或安全相关的应用中。本文提出一种新颖的面向语义分割问题的公平持续学习方法。具体而言，在公平性目标下，基于类别分布提出了一个新的公平持续学习框架。随后，提出了一种新颖的原型对比聚类损失，以应对持续学习中的重大挑战，即灾难性遗忘和背景偏移。所提出的损失还被证明是持续学习中常用知识蒸馏的一种新颖且广义的学习范式。此外，所提出的条件结构一致性损失进一步正则化了预测分割的结构约束。所提出方法在 ADE20K、Cityscapes 和 Pascal VOC 三个标准场景理解基准上取得了 State-of-the-Art 性能，并提升了分割模型的公平性。
英文摘要：
Continual semantic segmentation aims to learn new classes while maintaining the information from the previous classes. Although prior studies have shown impressive progress in recent years, the fairness concern in the continual semantic segmentation needs to be better addressed. Meanwhile, fairness is one of the most vital factors in deploying the deep learning model, especially in human-related or safety applications. In this paper, we present a novel Fairness Continual Learning approach to the semantic segmentation problem. In particular, under the fairness objective, a new fairness continual learning framework is proposed based on class distributions. Then, a novel Prototypical Contrastive Clustering loss is proposed to address the significant challenges in continual learning, i.e., catastrophic forgetting and background shift. Our proposed loss has also been proven as a novel, generalized learning paradigm of knowledge distillation commonly used in continual learning. Moreover, the proposed Conditional Structural Consistency loss further regularized the structural constraint of the predicted segmentation. Our proposed approach has achieved State-of-the-Art performance on three standard scene understanding benchmarks, i.e., ADE20K, Cityscapes, and Pascal VOC, and promoted the fairness of the segmentation model.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
