Gated Hierarchical Attention for Image Captioning
arXiv:1810.12535
Abstract
Attention modules connecting encoder and decoders have been widely applied in the field of object recognition, image captioning, visual question answering and neural machine translation, and significantly improves the performance. In this paper, we propose a bottom-up gated hierarchical attention (GHA) mechanism for image captioning. Our proposed model employs a CNN as the decoder which is able to learn different concepts at different layers, and apparently, different concepts correspond to different areas of an image. Therefore, we develop the GHA in which low-level concepts are merged into high-level concepts and simultaneously low-level attended features pass to the top to make predictions. Our GHA significantly improves the performance of the model that only applies one level attention, for example, the CIDEr score increases from 0.923 to 0.999, which is comparable to the state-of-the-art models that employ attributes boosting and reinforcement learning (RL). We also conduct extensive experiments to analyze the CNN decoder and our proposed GHA, and we find that deeper decoders cannot obtain better performance, and when the convolutional decoder becomes deeper the model is likely to collapse during training.
arXiv commentAccepted by ACCV
References in corpus (12)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Convolutional Sequence to Sequence Learning
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- Improved Image Captioning via Policy Gradient optimization of SPIDEr
- Image Captioning with Semantic Attention
- Learn To Pay Attention
- Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
- CNN+CNN: Convolutional Decoders for Image Captioning
- Multimodal Convolutional Neural Networks for Matching Image and Sentence
- Learning to Evaluate Image Captioning
- Dual Recurrent Attention Units for Visual Question Answering