跳到主要导航 跳到搜索 跳到主要内容

Geometry-Stable Class-Incremental Semantic Segmentation

  • Xiang Song
  • , Ziye Yang
  • , Yuhang He
  • , Jie Chen
  • , Danilo Comminiello
  • , Yihong Gong
  • Xi'an Jiaotong University
  • Northwestern Polytechnical University Xian
  • University of Rome La Sapienza

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

Class-Incremental Semantic Segmentation (CISS) requires a model to continually learn to segment new classes without forgetting previously learned ones. Existing CISS methods attempt to preserve old knowledge by replaying or mimicking past predictions. However, they fail to stabilize the underlying feature geometry under shifting background semantics, leading to prototype drift and forgetting. To address this problem, we propose a geometry-stable CISS paradigm that imposes an Orthogonal Equiangular Tight Frame (O-ETF) classifier. Our O-ETF keeps all foreground prototypes on a simplex ETF while assigning the background a dedicated prototype strictly orthogonal to the foreground span. This decouples background supervision from foreground semantics, providing geometry-guided supervision that helps mitigate foreground-background interference under background semantic shift. Based on this geometry, we build a shared-encoder and task-specific-decoder framework, where lightweight LoRA modules are used to adapt each decoder branch to newly introduced classes. During inference, we further design a Bayesian product-of-experts (Bayes-PoE) fusion strategy, which lifts branch-level predictions to the accumulated global label space and aggregates them in the shared O-ETF semantic space. Extensive experiments on ADE20K and Pascal VOC 2012 demonstrate the effectiveness of our method.

学术指纹

探究 'Geometry-Stable Class-Incremental Semantic Segmentation' 的科研主题。它们共同构成独一无二的学术指纹。

引用此