Multi-label image recognition is a task that predicts a set of object labels in an image. As the objects co-occur in the physical world, it is desirable to model label dependencies. Previous existing methods resort to either recurrent networks or pre-defined label correlation graphs for this purpose. In this paper, instead of using a pre-defined graph which is inflexible and may be sub-optimal for multi-label classification, we propose the A-GCN, which leverages the popular Graph Convolutional Networks with an Adaptive label correlation graph to model label dependencies. Specifically, we introduce a plug-and-play Label Graph (LG) module to learn label correlations with word embeddings, and then utilize traditional GCN to map this graph into label-dependent object classifiers which are further applied to image features. The basic LG module incorporates two 1 × 1 convolutional layers and uses the dot product to generate label graphs. In addition, we propose a sparse correlation constraint to enhance the LG module, and also explore different LG architectures. We validate our method on two diverse multi-label datasets: MS-COCO and Fashion550K. Experimental results show that our A-GCN significantly improves baseline methods and achieves performance superior or comparable to the state of the art.

多标签图像识别是一项预测图像中的一组对象标签的任务。由于对象在物理世界中同时出现，因此需要对标签依赖性进行建模。为此，先前的现有方法求助于循环网络或预定义的标签相关图。在本文中，而不是使用预先定义的曲线图，其是不灵活的，并且可以是次优的多标签分类，我们提出A-GCN，它利用流行ģ拍摄和Ç onvolutional Ñ与etworks甲适应性标签相关图可以对标签依赖性进行建模。具体来说，我们引入了一个即插即用的标签图（LG）模块，以学习与词嵌入的标签相关性，然后利用传统的GCN将该图映射到依赖标签的对象分类器中，这些分类器将进一步应用于图像特征。基本的LG模块包含两个1×1卷积层，并使用点积生成标签图。此外，我们提出了一种稀疏的相关约束来增强LG模块，并探索了不同的LG体系结构。我们在两个不同的多标签数据集上验证了我们的方法：MS-COCO和Fashion550K。实验结果表明，我们的A-GCN显着改善了基线方法，并实现了优于或可比的性能。