arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.03044cs.LGcs.CV
收藏

显示、注意和讲述:具有视觉注意力的神经图像标题生成

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard Zemel, Yoshua Bengio

摘要:

受最近机器翻译和目标检测工作的启发,我们引入了一个基于注意力的模型,它可以自动学习描述图像的内容。我们描述了我们如何可以训练这个模型在一个确定性的方式使用标准的反向传播技术和随机最大化的变分下限。我们还通过可视化展示了模型如何能够自动学习将目光固定在突出对象上,同时在输出序列中生成相应的单词。我们在三个基准数据集上验证了注意力的使用:Flickr8k,Flickr30k和MS COCO。

英文摘要:

Inspired by recent work in machine translation and object detection, we introduce an attention based model that automatically learns to describe the content of images. We describe how we can train this model in a deterministic manner using standard backpropagation techniques and stochastically by maximizing a variational lower bound. We also show through visualization how the model is able to automatically learn to fix its gaze on salient objects while generating the corresponding words in the output sequence. We validate the use of attention with state-of-the-art performance on three benchmark datasets: Flickr8k, Flickr30k and MS COCO.

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。

↑