论文标题
Vilio：最新的visio语言模型应用于可恨模因
Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes
论文作者
论文摘要
这项工作介绍了Vilio，这是一种最先进的Visio语言模型及其在可恨模因数据集中的应用。实施的模型已安装到统一的代码库中，并已更改以产生更好的性能。 Vilio的目标是为任何Visio-Linuistic问题提供一个用户友好的起点。在Vilio中实施的5种不同V+L模型的合奏在3300名参与者中获得了可恨模因挑战中的第二名。该代码可在https://github.com/muennighoff/vilio上找到。
This work presents Vilio, an implementation of state-of-the-art visio-linguistic models and their application to the Hateful Memes Dataset. The implemented models have been fitted into a uniform code-base and altered to yield better performance. The goal of Vilio is to provide a user-friendly starting point for any visio-linguistic problem. An ensemble of 5 different V+L models implemented in Vilio achieves 2nd place in the Hateful Memes Challenge out of 3,300 participants. The code is available at https://github.com/Muennighoff/vilio.
