通过选择性迁移旧类上下文，缓解增量分割中的遗忘问题。
SELECT: SELEctive Context Transfer for Class-Incremental Semantic Segmentation
- 基于语义相似度筛选旧类，仅向新类传递相关上下文
- 引入噪声扰动和边界损失，防止信息污染
- 在Pascal VOC和ADE20K上分别提升2.2%和2.8%的平均交并比
类别增量语义分割（CISS）面临灾难性遗忘和背景漂移的挑战，学习新类别会损害对旧类别的性能。现有方法虽试图平衡稳定性与可塑性，但常因盲目知识迁移或模糊初始化而稀释关键语义信息。为此，我们提出SELECT，一种选择性上下文迁移方法，将每个新类别建立在少数语义相似的旧类别基础上。其核心是上下文转移注意力机制，将相似类别的已学特征向量聚合为新类别的结构化初始化。为防止借用表示被污染，我们引入可控噪声扰动和基于边距的上下文迁移损失，强制新类特征与源特征分离。在Pascal VOC和ADE20K上的大量实验表明，SELECT持续优于先前方法，在VOC上实现2.2%的mIoU提升，在ADE20K上提升2.8%，有效缓解了稳定-可塑困境。代码已开源。
原文摘要 · Abstract (English)
Class-Incremental Semantic Segmentation (CISS) is fundamentally challenged by catastrophic forgetting and background shift, where learning new concepts degrades performance on previously seen classes. While existing methods attempt to balance stability (retaining old knowledge) and plasticity (learning new knowledge), they often fail to leverage prior knowledge effectively. These approaches typically rely on indiscriminate knowledge transfer or ambiguous initializations, which can dilute crucial semantic information. To overcome this limitation, we propose SELECT, a novel approach for Selective Context Transfer, which instead grounds each new class in a small set of semantically similar past classes. Its core is a Context Transfer Attention mechanism that aggregates the learned tokens from similar classes into a structured initialization for the new class. To ensure this transfer does not corrupt the borrowed representations, we add a controlled noise perturbation and a margin-based context-transfer loss that enforces separation between the new class token and its source tokens. Extensive experiments on Pascal VOC and ADE20K show that SELECT consistently outperforms prior work, achieving mIoU of 2.2% on VOC and 2.8% on ADE, providing an effective handle on the stability-plasticity dilemma. Code is available at https://github.com/avigupta2798/SELECT.
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。