B-SCST：用于图像描述的贝叶斯自判别序列训练
B-SCST: Bayesian Self-Critical Sequence Training for Image Captioning
摘要：
贝叶斯深度神经网络（DNN）可以提供一个有数学基础的框架来量化来自图像描述模型的预测中的不确定性。我们提出了一种贝叶斯变体的基于策略梯度的强化学习训练技术，用于图像描述模型，以直接优化不可区分的图像描述质量指标，如CIDEr-D。我们扩展了著名的自我关键序列训练（SCST）方法的图像描述模型，通过将贝叶斯推理，并将其称为B-SCST。B-SCST中的策略梯度的“基线”是通过对从使用贝叶斯DNN模型获得的分布中提取的字幕的预测质量度量（CIDEr-D）进行平均来生成的。我们推断这个预测分布使用蒙特卡罗（MC）辍学近似变分推断。我们表明，B-SCST提高CIDEr-D分数Flickr 30 k，MS COCO和VizWiz图像描述数据集相比，SCST的方法。我们还提供了一个研究的不确定性量化的预测字幕，并证明它与CIDER-D分数。据我们所知，这是第一次这样的分析，它可以提高图像描述模型输出的可解释性，这对实际应用至关重要。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
