# B-SCST: Bayesian Self-Critical Sequence Training for Image Captioning

arXiv: https://arxiv.org/abs/2004.02435 · HTML: https://mlsanity.com/paper/2004.02435/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2020.

## Built on by (most cited first, 3 of 3)

- [AVD2: Accident Video Diffusion for Accident Video Description](https://mlsanity.com/paper/2502.14801/) (2025)
- [Partially-Supervised Novel Object Captioning Leveraging Context from Paired Data](https://mlsanity.com/paper/2109.05115/) (2021)
- [Variational Transformer: A Framework Beyond the Trade-off between Accuracy and Diversity for Image Captioning](https://mlsanity.com/paper/2205.14458/) (2022)

## Abstract (arXiv)

Bayesian deep neural networks (DNNs) can provide a mathematically grounded framework to quantify uncertainty in predictions from image captioning models. We propose a Bayesian variant of policy-gradient based reinforcement learning training technique for image captioning models to directly optimize non-differentiable image captioning quality metrics such as CIDEr-D. We extend the well-known Self-Critical Sequence Training (SCST) approach for image captioning models by incorporating Bayesian inference, and refer to it as B-SCST. The "baseline" for the policy-gradients in B-SCST is generated by averaging predictive quality metrics (CIDEr-D) of the captions drawn from the distribution obtained using a Bayesian DNN model. We infer this predictive distribution using Monte Carlo (MC) dropout approximate variational inference. We show that B-SCST improves CIDEr-D scores on Flickr30k, MS COCO and VizWiz image captioning datasets, compared to the SCST approach. We also provide a study of uncertainty quantification for the predicted captions, and demonstrate that it correlates well with the CIDEr-D scores. To our knowledge, this is the first such analysis, and it can improve the interpretability of image captioning model outputs, which is critical for practical applications.