Reflective Decoding Network for Image Captioning
arXiv:1908.11824
Abstract
State-of-the-art image captioning methods mostly focus on improving visual features, less attention has been paid to utilizing the inherent properties of language to boost captioning performance. In this paper, we show that vocabulary coherence between words and syntactic paradigm of sentences are also important to generate high-quality image caption. Following the conventional encoder-decoder framework, we propose the Reflective Decoding Network (RDN) for image captioning, which enhances both the long-sequence dependency and position perception of words in a caption decoder. Our model learns to collaboratively attend on both visual and textual features and meanwhile perceive each word's relative position in the sentence to maximize the information delivered in the generated caption. We evaluate the effectiveness of our RDN on the COCO image captioning datasets and achieve superior performance over the previous methods. Further experiments reveal that our approach is particularly advantageous for hard cases with complex scenes to describe by captions.
arXiv commentICCV 2019
References in corpus (17)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Sequence to Sequence Learning with Neural Networks
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- Convolutional Sequence to Sequence Learning
- Microsoft COCO Captions: Data Collection and Evaluation Server
- A Deep Reinforced Model for Abstractive Summarization
- Professor Forcing: A New Algorithm for Training Recurrent Networks
- Image Captioning with Semantic Attention
- Language Models for Image Captioning: The Quirks and What Works
- MAttNet: Modular Attention Network for Referring Expression Comprehension
- Review Networks for Caption Generation
- Coherent Dialogue with Attention-based Language Models
- Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present
- Recurrent Memory Networks for Language Modeling
- Self-Attentive Residual Decoder for Neural Machine Translation