arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.00599cs.CVcs.LG
收藏

一个实现的“猜猜谁?“使用CLIP的游戏

An implementation of the "Guess who?" game using CLIP

Valencian International University(瓦伦西亚国际大学);Dimai S.L.(Dimai有限公司);Universidad Politécnica de Madrid(马德里理工大学)

Arnau Martí Sarri, Victor Rodriguez-Fernandez

摘要:

CLIP(对比图像预训练)是一种从自然语言监督中学习计算机视觉任务的有效方法,由于其zero-shot传输功能,最近在深度学习方面取得了突破。通过从互联网上提供的图像-文本对进行训练,CLIP模型可以轻松地转移到大多数任务,而不需要任何数据集特定的训练。在这项工作中,我们使用CLIP来实现流行游戏“猜猜谁?”的引擎。“,使得玩家使用自然语言提示与游戏交互,并且CLIP自动决定游戏板中的图像是否满足该提示。我们研究了这种方法的性能,通过基准测试不同的方式提示问题的CLIP,并显示其zero-shot能力的局限性。

英文摘要:

CLIP (Contrastive Language-Image Pretraining) is an efficient method for learning computer vision tasks from natural language supervision that has powered a recent breakthrough in deep learning due to its zero-shot transfer capabilities. By training from image-text pairs available on the internet, the CLIP model transfers non-trivially to most tasks without the need for any data set specific training. In this work, we use CLIP to implement the engine of the popular game "Guess who?", so that the player interacts with the game using natural language prompts and CLIP automatically decides whether an image in the game board fulfills that prompt or not. We study the performance of this approach by benchmarking on different ways of prompting the questions to CLIP, and show the limitations of its zero-shot capabilites.

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。

↑