提出EASe框架，实现复杂场景下无需标注的细粒度语义分割。
Excite, Attend and Segment (EASe): Domain-Agnostic Fine-Grained Mask Discovery with Feature Calibration and Self-Supervised Upsampling
- 通过通道激励与空间注意力融合，提升低分辨率特征的细节表达。
- 在多个复杂形态数据集上超越现有最优方法，平均性能提升5.3%。
- 无需训练，适合快速部署于真实世界多变场景的细粒度分割任务。
无监督分割方法越来越多地利用基础模型（FM）来提升显著目标发现能力。然而，在具有复杂多组件结构的场景中，这些方法常因缺乏精细结构细节而表现不佳。许多最先进的无监督分割流程依赖于粗粒度的块级表示进行掩码发现，这种表示会抑制解析复杂形态所需的细粒度信息。为此，我们提出Excite, Attend and Segment（EASe），一种无需领域知识的无监督语义分割框架，可高效实现挑战性真实场景中的细粒度掩码发现。EASe采用新颖的语义感知上采样与通道激励（SAUCE）机制，对低分辨率FM特征通道进行选择性校准，并跨空间编码的图像与FM特征进行注意力聚合，以恢复全分辨率语义表征。最后，采用无需训练的提示注意力特征聚合器（CAFE），利用SAUCE注意力得分作为语义分组信号，将聚合特征分割为多粒度掩码。EASe及其核心组件SAUCE与CAFE均直接作用于像素级特征表示，实现精准的细粒度密集语义掩码发现。评估结果表明，EASe在主流标准基准和多种具复杂形态的数据集上均优于先前最先进方法。代码已公开于 https://ease-project.github.io
原文摘要 · Abstract (English)
Unsupervised segmentation approaches have increasingly leveraged foundation models (FM) to improve salient object discovery. However, these methods often falter in scenes with complex, multi-component morphologies, where fine-grained structural detail is indispensable. Many state-of-the-art unsupervised segmentation pipelines rely on mask discovery approaches that utilize coarse, patch-level representations. These coarse representations inherently suppress the fine-grained detail required to resolve such complex morphologies. To overcome this limitation, we propose Excite, Attend and Segment (EASe), an unsupervised domain-agnostic semantic segmentation framework for easy fine-grained mask discovery across challenging real-world scenes. EASe utilizes novel Semantic-Aware Upsampling with Channel Excitation (SAUCE) to excite low-resolution FM feature channels for selective calibration and attends across spatially-encoded image and FM features to recover full-resolution semantic representations. Finally, EASe segments the aggregated features into multi-granularity masks using a novel training-free Cue-Attentive Feature Aggregator (CAFE) which leverages SAUCE attention scores as a semantic grouping signal. EASe, together with SAUCE and CAFE, operate directly at pixel-level feature representations to enable accurate fine-grained dense semantic mask discovery. Our evaluation demonstrates superior performance of EASe over previous state-of-the-arts (SOTAs) across major standard benchmarks and diverse datasets with complex morphologies. Code is available at https://ease-project.github.io
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。