arXiv 2603.175202026-03-18cs.CV

PCA-Seg：重新审视开放词汇语义和部分分割中的成本聚合

PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation

Nanjing University of Science and Technology（南京理工大学）；Nanjing Normal University（南京师范大学）；Department of Electrical and Computer Engineering, Sungkyunkwan University（成均馆大学电子与计算机工程系）；University of Electronic Science and Technology of China（电子科技大学）；State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery（先进施工机械智能制造国家重点实验室）

Jianjian Yin, Tao Chen, Yi Chen, Gensheng Pei, Xiangbo Shu, Yazhou Yao, Fumin Shen

备注：: Accepted by CVPR2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出PCA-Seg方法，通过并行成本聚合缓解类级语义与空间上下文之间的知识干扰，提升开放词汇语义和部分分割性能。

摘要：

最近视觉-语言模型（VLMs）在开放词汇语义和部分分割（OSPS）中取得了显著进展。然而，现有方法通过空间和类别的串行结构从成本体积中提取图像-文本对齐线索，导致类级语义与空间上下文之间的知识干扰。为此，本文提出了一种简单而有效的并行成本聚合（PCA-Seg）范式，以缓解上述挑战，使模型能够从成本体积中捕捉更丰富的视觉-语言对齐信息。具体而言，我们设计了一个专家驱动的感知学习（EPL）模块，该模块高效地整合语义和上下文流。它结合了多专家解析器，从多个视角提取互补特征。此外，设计了一个系数映射器，用于自适应地学习每个像素特定的权重，以将互补知识整合到统一且稳健的特征嵌入中。进一步地，我们提出了一种特征正交化解耦（FOD）策略，以缓解语义和上下文流之间的冗余，使EPL模块能够从正交化特征中学习多样化的知识。在八个基准测试中，广泛实验表明，PCA-Seg中的每个并行块仅增加0.35M参数，同时实现了最先进的OSPS性能。

英文摘要：

Recent advances in vision-language models (VLMs) have garnered substantial attention in open-vocabulary semantic and part segmentation (OSPS). However, existing methods extract image-text alignment cues from cost volumes through a serial structure of spatial and class aggregations, leading to knowledge interference between class-level semantics and spatial context. Therefore, this paper proposes a simple yet effective parallel cost aggregation (PCA-Seg) paradigm to alleviate the above challenge, enabling the model to capture richer vision-language alignment information from cost volumes. Specifically, we design an expert-driven perceptual learning (EPL) module that efficiently integrates semantic and contextual streams. It incorporates a multi-expert parser to extract complementary features from multiple perspectives. In addition, a coefficient mapper is designed to adaptively learn pixel-specific weights for each feature, enabling the integration of complementary knowledge into a unified and robust feature embedding. Furthermore, we propose a feature orthogonalization decoupling (FOD) strategy to mitigate redundancy between the semantic and contextual streams, which allows the EPL module to learn diverse knowledge from orthogonalized features. Extensive experiments on eight benchmarks show that each parallel block in PCA-Seg adds merely 0.35M parameters while achieving state-of-the-art OSPS performance.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。