arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.13670cs.CV
收藏

什么是视觉上下文学习的好例子?

What Makes Good Examples for Visual In-Context Learning?

Nanyang Technological University(南洋理工大学)

Yuanhan Zhang, Kaiyang Zhou, Ziwei Liu

摘要:

在广泛数据上训练的大规模模型由于其强大的泛化性能,近年来已成为计算机视觉的主流体系结构。在本文中,主要关注的是大型视觉模型中的一种新兴能力,称为上下文学习,它允许通过对上下文示例进行条件化来推断看不见的任务(也称为~提示),而不更新模型参数。这个概念在自然语言处理中是众所周知的,但直到最近才针对大型视觉模型进行了研究。我们首次对计算机视觉中上下文样例的影响进行了全面的研究,发现上下文样例的选择对性能具有高度的敏感性。为了克服这个问题,我们提出了一个提示检索框架,自动选择的上下文中的例子。具体来说,我们提出了(1)一个无监督的提示检索方法的基础上最近的例子搜索使用现成的模型,和(2)监督提示检索方法,训练神经网络选择的例子,直接最大限度地提高上下文学习性能。实验结果表明,与常用的随机选择方法相比,我们的方法可以为视觉上下文学习带来显著的改进。

英文摘要:

Large-scale models trained on broad data have recently become the mainstream architecture in computer vision due to their strong generalization performance. In this paper, the main focus is on an emergent ability in large vision models, known as in-context learning, which allows inference on unseen tasks by conditioning on in-context examples (a.k.a.~prompt) without updating the model parameters. This concept has been well-known in natural language processing but has only been studied very recently for large vision models. We for the first time provide a comprehensive investigation on the impact of in-context examples in computer vision, and find that the performance is highly sensitive to the choice of in-context examples. To overcome the problem, we propose a prompt retrieval framework to automate the selection of in-context examples. Specifically, we present (1) an unsupervised prompt retrieval method based on nearest example search using an off-the-shelf model, and (2) a supervised prompt retrieval method, which trains a neural network to choose examples that directly maximize in-context learning performance. The results demonstrate that our methods can bring non-trivial improvements to visual in-context learning in comparison to the commonly-used random selection.

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。

↑