arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.02818cs.CVcs.AIcs.CY
收藏

评估CLIP:对更广泛能力和下游影响的描述

Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications

OpenAI(OpenAI(开放人工智能研究中心));AI Index(人工智能指数)

Sandhini Agarwal, Gretchen Krueger, Jack Clark, Alec Radford, Jong Wook Kim, Miles Brundage

摘要:

最近,随着诸如CLIP和ALIGN的模型的出现,在更可推广的计算机视觉(“CV”)模型中已经有了突破。在本文中,我们分析了CLIP,并强调了这些模型带来的一些挑战。CLIP减少了对特定任务训练数据的需求,可能会为自动化打开许多利基任务。CLIP还允许用户灵活地用自然语言指定图像分类类,我们发现这可以改变偏见的表现方式。此外,通过一些初步的探索,我们发现,CLIP可以继承在以前的计算机视觉系统中发现的偏见。考虑到这些模型的广泛和不可预测的使用领域,这就提出了关于这些系统的足够安全的行为可能看起来像什么的问题。这些结果为越来越多的工作提供了证据,这些工作要求改变“更好”模型的概念-超越简单地关注面向任务的能力评估的更高准确性,并朝着更广泛的“更好”考虑部署关键功能,例如不同的使用环境,以及在考虑模型部署时与模型交互的人。

英文摘要:

Recently, there have been breakthroughs in computer vision ("CV") models that are more generalizable with the advent of models such as CLIP and ALIGN. In this paper, we analyze CLIP and highlight some of the challenges such models pose. CLIP reduces the need for task specific training data, potentially opening up many niche tasks to automation. CLIP also allows its users to flexibly specify image classification classes in natural language, which we find can shift how biases manifest. Additionally, through some preliminary probes we find that CLIP can inherit biases found in prior computer vision systems. Given the wide and unpredictable domain of uses for such models, this raises questions regarding what sufficiently safe behaviour for such systems may look like. These results add evidence to the growing body of work calling for a change in the notion of a 'better' model--to move beyond simply looking at higher accuracy at task-oriented capability evaluations, and towards a broader 'better' that takes into account deployment-critical features such as different use contexts, and people who interact with the model when thinking about model deployment.

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。

↑