English

Hidden State Guidance: Improving Image Captioning using An Image Conditioned Autoencoder

Computer Vision and Pattern Recognition 2020-01-16 v2 Computation and Language

Abstract

Most RNN-based image captioning models receive supervision on the output words to mimic human captions. Therefore, the hidden states can only receive noisy gradient signals via layers of back-propagation through time, leading to less accurate generated captions. Consequently, we propose a novel framework, Hidden State Guidance (HSG), that matches the hidden states in the caption decoder to those in a teacher decoder trained on an easier task of autoencoding the captions conditioned on the image. During training with the REINFORCE algorithm, the conventional rewards are sentence-based evaluation metrics equally distributed to each generated word, no matter their relevance. HSG provides a word-level reward that helps the model learn better hidden representations. Experimental results demonstrate that HSG clearly outperforms various state-of-the-art caption decoders using either raw images or detected objects as inputs.

Keywords

Cite

@article{arxiv.1910.14208,
  title  = {Hidden State Guidance: Improving Image Captioning using An Image Conditioned Autoencoder},
  author = {Jialin Wu and Raymond J. Mooney},
  journal= {arXiv preprint arXiv:1910.14208},
  year   = {2020}
}
R2 v1 2026-06-23T12:00:16.547Z