A parallel-fusion RNN-LSTM architecture for image caption generation

• Main Authors: Minsi Wang, Li Song, Xiaokang Yang, Chuanfei Luo
• Format: Conference Proceeding
• Language: English
• Subjects: Computational modeling; Data models; deep neural network; Feature extraction; Image captioning; LSTM; Measurement; Recurrent neural networks; RNN; Training
• ISSN: 2381-8549
• DOI: 10.1109/ICIP.2016.7533201

The models based on deep convolutional networks and recurrent neural networks have dominated in recent image caption generation tasks. Performance and complexity are still eternal topic. Inspired by recent work, by combining the advantages of simple RNN and LSTM, we present a novel parallel-fusion RNN-LSTM architecture, which obtains better results than a dominated one and improves the efficiency as well. The proposed approach divides the hidden units of RNN into several same-size parts, and lets them work in parallel. Then, we merge their outputs with corresponding ratios to generate final results. Moreover, these units can be different types of RNNs, for instance, a simple RNN and a LSTM. By training normally using NeuralTalk 1 platform on Flickr8k dataset, without additional training data, we get better results than that of dominated structure and particularly, the proposed model surpass GoogleNIC in image caption generation.