Recent state-of-the-art approaches of multi-label image classification exploit the label dependencies at the global level, largely improving the labeling ability. However, accurately predicting small objects and visual concepts is still challenging due to the limited discrimination of the global visual features. In this paper, we propose a Regional Latent Semantic Dependencies model (RLSD) to address this problem. The utilized model includes a fully convolutional localization architecture to localize the regions that may contain multiple highly-dependent labels. The localized regions are further sent to the recurrent neural networks (RNN) to characterize the latent semantic dependencies at the regional level. Experimental results on several benchmark datasets show that our proposed model achieves the best performance compared to the state-of-the-art models, especially for predicting small objects occurred in the images. In addition, we set up an upper bound model (RLSD+ft-RPN) using bounding box coordinates during training, the experimental results also show that our RLSD can approach the upper bound without using the bounding-box annotations, which is more realistic in the real world.

本论文提出了一种区域潜在语义依赖模型，该模型使用卷积神经网络和递归神经网络相结合，能够有效预测多标签图像分类中小物体和视觉概念，同时不需要使用边框注释实现最佳性能。

基于区域潜在语义相关性的多标签图像分类