CVAug 20, 2019

Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition

arXiv:1908.07325v1348 citationsHas Code
AI Analysis

This addresses the challenge of accurately recognizing multiple labels in images for computer vision applications, representing an incremental advance over existing methods.

The paper tackles the problem of multi-label image recognition by proposing a Semantic-Specific Graph Representation Learning (SSGRL) framework to improve semantic region localization and label dependency modeling, resulting in mAP improvements of 2.5% to 6.7% on benchmarks like PASCAL VOC, COCO, and Visual Genome.

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.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes