通过分层成本聚合与结构引导，提升未知类别物体细粒度分割精度。
Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation
- 分设物体与部件级成本聚合，精准定位细粒度部分
- 在3个数据集上超越现有方法，显著提升对未见类别的泛化能力
- 适合需要细粒度语义分割的开放词汇场景
开放词汇部件分割（OVPS）旨在识别未见类别中的细粒度部件。本文指出两大挑战：部件级图像-文本对齐困难，以及部件分割缺乏结构理解。为此提出PartCATSeg框架，融合对象感知的部件级成本聚合、组合损失及来自DINO的结构引导。采用解耦成本聚合策略，分别处理对象与部件级成本，提升部件分割精度；引入组合损失以更好建模部件-对象关系，弥补部件标注不足；利用DINO特征提供结构引导，改善边界划分与部件间关系理解。在Pascal-Part-116、ADE20K-Part-234和PartImageNet三个数据集上的实验表明，该方法显著优于现有先进方法，为未见部件类别的鲁棒泛化设立了新基准。
原文摘要 · Abstract (English)
Open-Vocabulary Part Segmentation (OVPS) is an emerging field for recognizing fine-grained parts in unseen categories. We identify two primary challenges in OVPS: (1) the difficulty in aligning part-level image-text correspondence, and (2) the lack of structural understanding in segmenting object parts. To address these issues, we propose PartCATSeg, a novel framework that integrates object-aware part-level cost aggregation, compositional loss, and structural guidance from DINO. Our approach employs a disentangled cost aggregation strategy that handles object and part-level costs separately, enhancing the precision of part-level segmentation. We also introduce a compositional loss to better capture part-object relationships, compensating for the limited part annotations. Additionally, structural guidance from DINO features improves boundary delineation and inter-part understanding. Extensive experiments on Pascal-Part-116, ADE20K-Part-234, and PartImageNet datasets demonstrate that our method significantly outperforms state-of-the-art approaches, setting a new baseline for robust generalization to unseen part categories.
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。