SFR-Net：多标签零样本下水道缺陷检测中的引导-融合-精炼网络
SFR-Net: Steering-Fusion-Refining Network in Multi-label Zero-Shot Sewer Defect Detection
针对稀疏语义描述与复杂管道视觉环境之间的对齐歧义问题，提出参数高效的特征引导（steering）机制与解耦的全局/局部多粒度证据融合，并用已见类的关系逻辑迁移做分数校正；这套「引导-融合-精炼」范式可迁移到其他开放词表/零样本检测任务中缓解视觉-语义对齐歧义。
原文依据 existing methods struggle to establish robust and fine-grained visual-semantic alignment between the complex visual environment inside the pipes and the often sparse semantic descriptions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论由于数据标注成本高昂，且无法为所有缺陷类别获取充足的样本数据，市政下水道管道缺陷检测对传统模型而言面临显著的泛化挑战。多标签零样本学习（ML-ZSL）为应对这一挑战提供了可行方案。然而，现有方法难以在管道内部复杂的视觉环境与往往稀疏的语义描述之间建立稳健且细粒度的视觉-语义对齐，从而导致一个关键问题：对齐歧义。为缓解该问题，我们提出一种新颖的引导-融合-精炼网络（SFR-Net），遵循三阶段范式逐步消解这种歧义。具体而言，表征引导（RS）模块首先引入参数高效的特征引导机制，使表征持续适配管道场景；多粒度证据融合（MEF）模块随后通过解耦的全局与局部路径聚合无歧义的多粒度视觉证据；广义关系分数精炼（GR）模块最终学习并迁移已见缺陷中的关系逻辑，从而获得通用的分数校正能力，直接精炼初步预测分数，显著提升模型的零样本泛化能力与预测一致性。在公开的 Sewer-ML 数据集与我们私有的 WZ-Pipe 数据集上的大量实验表明，所提出的 SFR-Net 在多标签零样本学习任务上取得了最优性能。
英文原文摘要 1596 字符
Due to the prohibitive cost of data annotation and the inability to obtain sufficient sample data for all defect categories, municipal sewer pipe defect detection poses significant generalization challenges for traditional models. Multi-Label Zero-Shot Learning (ML-ZSL) offers a viable solution to address this challenge. However, existing methods struggle to establish robust and fine-grained visual-semantic alignment between the complex visual environment inside the pipes and the often sparse semantic descriptions, leading to a critical issue: Alignment Ambiguity. To mitigate this, we propose a novel Steering-Fusion-Refining Network (SFR-Net) that follows a three-stage paradigm to progressively dissolve this ambiguity. This is achieved as the Representation Steering (RS) module first integrates a parameter-efficient feature steering mechanism to continuously adapt the representation to the pipe scene; the Multi-Granularity Evidence Fusion (MEF) module subsequently aggregates unambiguous multi-granularity visual evidence through decoupled global and local paths; and the Generalized Relational Score Refining (GR) module ultimately learns and transfers relational logic from seen defects to gain a universal score correction ability, directly refining preliminary prediction scores and significantly boosting the model's zero-shot generalization and prediction consistency. Extensive experiments on the public Sewer-ML dataset and our private WZ-Pipe dataset demonstrate that the proposed SFR-Net achieves state-of-the-art (SOTA) performance in multi-label zero-shot learning task.