论文标题
学习图像字幕的紧凑奖励
Learning Compact Reward for Image Captioning
论文作者
论文摘要
对抗性学习表明，在图像字幕中生成自然和多样化的描述方面的进步。但是，由于奖励歧义问题，现有的对抗方法对现有的对抗方法的奖励含糊不清。在本文中，我们提出了一种精致的对抗性逆增强学习（RAIRL）方法，以通过在句子中解开每个单词的奖励来处理奖励歧义问题，并通过完善损失功能将发生器转移到NASH平衡中，从而实现稳定的对抗训练。此外，我们在损失函数中引入条件术语以减轻模式崩溃并增加生成的描述的多样性。我们在Coco和Flickr30k上的实验表明，我们的方法可以学习图像字幕的紧凑奖励。
Adversarial learning has shown its advances in generating natural and diverse descriptions in image captioning. However, the learned reward of existing adversarial methods is vague and ill-defined due to the reward ambiguity problem. In this paper, we propose a refined Adversarial Inverse Reinforcement Learning (rAIRL) method to handle the reward ambiguity problem by disentangling reward for each word in a sentence, as well as achieve stable adversarial training by refining the loss function to shift the generator towards Nash equilibrium. In addition, we introduce a conditional term in the loss function to mitigate mode collapse and to increase the diversity of the generated descriptions. Our experiments on MS COCO and Flickr30K show that our method can learn compact reward for image captioning.
