Recognizing multiple labels of images is a practical and challenging task, and significant progress has been made by searching semantic-aware regions and modeling label dependency. However, current methods cannot locate the semantic regions accurately due to the lack of part-level supervision or semantic guidance. Moreover, they cannot fully explore the mutual interactions among the semantic regions and do not explicitly model the label co-occurrence. To address these issues, we propose a Semantic-Specific Graph Representation Learning (SSGRL) framework that consists of two crucial modules: 1) a semantic decoupling module that incorporates category semantics to guide learning semantic-specific representations and 2) a semantic interaction module that correlates these representations with a graph built on the statistical label co-occurrence and explores their interactions via a graph propagation mechanism. Extensive experiments on public benchmarks show that our SSGRL framework outperforms current state-of-the-art methods by a sizable margin, e.g. with an mAP improvement of 2.5%, 2.6%, 6.7%, and 3.1% on the PASCAL VOC 2007 & 2012, Microsoft-COCO and Visual Genome benchmarks, respectively. Our codes and models are available at https://github.com/HCPLab-SYSU/SSGRL.

提出了一种Semantic-Specific Graph Representation Learning (SSGRL)的框架，包含两个重要模块：语义解耦模块和语义交互模块，其中语义解耦模块结合类别语义以指导学习语义特定表示，语义交互模块则将这些表示与基于统计标签共现构建的图相互关联，可以通过图传播机制来探索它们的相互作用，通过大量的公共基准测试，证明SSGRL框架优于现有的最新方法。

学习语义特定图表示用于多标签图像识别