提出CIT方法，让模型在增量分割中不遗忘旧类且性能稳定。
CIT: Rethinking Class-incremental Semantic Segmentation with a Class Independent Transformation
- 用类无关转换将分割输出转为独立形式，避免类别依赖。
- 在ADE20K上11阶段任务遗忘低于5%，PASCAL VOC仅低于1%。
- 适合需要长期学习新类别的场景，如自动驾驶、医疗图像分析。
类别增量语义分割（CSS）要求模型在不遗忘旧类别的情况下学习新类别，通常通过知识蒸馏和引入最新数据实现。然而，现有基于类的方法依赖Softmax，强制类别间关联，导致初始任务与当前任务输出分布差异大，无法直接传递旧类结果。本文提出简单高效的类无关转换（CIT），将现有分割模型输出转化为类无关形式，开销极小且性能无损。借助CIT支持的类无关预测，构建累积蒸馏框架，确保所有类别信息均衡融合。在DeepLabV3、Mask2Former和SegViTv2等多种架构上进行大量实验，结果显示：在最挑战的11任务配置下，ADE20K上的任务遗忘低于5%；所有配置下PASCAL VOC 2012的遗忘均低于1%。
原文摘要 · Abstract (English)
Class-incremental semantic segmentation (CSS) requires that a model learn to segment new classes without forgetting how to segment previous ones: this is typically achieved by distilling the current knowledge and incorporating the latest data. However, bypassing iterative distillation by directly transferring outputs of initial classes to the current learning task is not supported in existing class-specific CSS methods. Via Softmax, they enforce dependency between classes and adjust the output distribution at each learning step, resulting in a large probability distribution gap between initial and current tasks. We introduce a simple, yet effective Class Independent Transformation (CIT) that converts the outputs of existing semantic segmentation models into class-independent forms with negligible cost or performance loss. By utilizing class-independent predictions facilitated by CIT, we establish an accumulative distillation framework, ensuring equitable incorporation of all class information. We conduct extensive experiments on various segmentation architectures, including DeepLabV3, Mask2Former, and SegViTv2. Results from these experiments show minimal task forgetting across different datasets, with less than 5% for ADE20K in the most challenging 11 task configurations and less than 1% across all configurations for the PASCAL VOC 2012 dataset.
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。