Dank学习：使用深度神经网络生成模因
Dank Learning: Generating Memes Using Deep Neural Networks
摘要：
我们介绍了一个新颖的模因生成系统，它可以产生一个幽默和相关的说明任何图像。此外，该系统不仅可以以图像为条件，还可以以与模因模板相关的用户定义的标签为条件，从而为用户提供关于模因内容的处理。该系统使用预训练的Inception-v3网络返回图像嵌入，该图像嵌入被传递到基于注意力的深层LSTM模型，以产生标题-受广泛认可的Show and Tell模型的启发。我们实现了一个修改后的束搜索，以鼓励多样性的字幕。我们评估我们的模型的质量，使用困惑和人类的评价上产生的模因的质量，以及它们是否可以从真正的区别。我们的模型产生了原始的模因，这些模因总体上不能与真实的模因区分开来。
英文摘要：
We introduce a novel meme generation system, which given any image can produce a humorous and relevant caption. Furthermore, the system can be conditioned on not only an image but also a user-defined label relating to the meme template, giving a handle to the user on meme content. The system uses a pretrained Inception-v3 network to return an image embedding which is passed to an attention-based deep-layer LSTM model producing the caption - inspired by the widely recognised Show and Tell Model. We implement a modified beam search to encourage diversity in the captions. We evaluate the quality of our model using perplexity and human assessment on both the quality of memes generated and whether they can be differentiated from real ones. Our model produces original memes that cannot on the whole be differentiated from real ones.
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。
