摘要： 现有图像描述模型存在解码端层次不深、训练效率低下的问题，且生成的描述语句在语言连贯性和内容多样性方面效果欠佳，为此，提出一种基于独立循环神经网络的深层图像描述模型Deep-NIC。采用独立循环神经元与批标准化方法构建解码单元，通过解码单元的多层叠加建立深层解码端。使用谷歌inception V3作为编码端，构建深层图像描述模型。在数据集MS COCO2014上进行对比实验，结果表明，与基线模型相比，Deep-NIC模型的BLEU-4、METEOR、CIDER评分分别提升3.2%、10.3%、8.18%，其更容易训练且具有更好的拟合效果。

关键词: 图像描述, 深层图像描述模型, 深层解码端, 独立循环神经网络, 批标准化

Abstract: The existing image description models face the challenges of low training efficiency, low level of the decoder, and the poor grammar coherence and content diversity of the generated descriptive sentences.To address the problem, a deep image description model, Deep-NIC, based on Independent Recurrent Neural Network(IndRNN) is proposed.The deep decoder unit is built using both independent recurrent neuron and the Batch Normalization(BN) method.Then based on the stacked multiple layers of decoder units, the deep decoder is established.Finally, the Google inception V3 has been used as the encoder to build a deep image description model.Experimental results on the data set MS COCO2014 show that compared to the baseline model NIC, the Deep-NIC model delivers a performance improvement of 3.2% under the BLEU-4 scoring standards, 10.3% under METEOR, and 8.18% under CIDER.The proposed model is easier to train, and can provide better fitting performance.

Key words: image description, deep image description model, deep decoder, Independent Recurrent Neural Network(IndRNN), Batch Normalization(BN)

中图分类号: 

• TP399