arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.15441cs.CVcs.AIcs.CLcs.LG
收藏

Zero-shot模型诊断

Zero-shot Model Diagnosis

Carnegie Mellon University(卡内基梅隆大学)

Jinqi Luo, Zhaoning Wang, Chen Henry Wu, Dong Huang, Fernando De la Torre

摘要:

在部署深度视觉模型时,这些系统的行为必须是可解释的,以确保对其可靠性和公平性的信心。评估深度学习模型的一种常见方法是构建一个带有感兴趣属性的标记测试集,并评估其性能。然而,创建平衡测试集(即,对所有重要特征进行均匀采样)通常是耗时、昂贵且易于出错的。我们试图解决的问题是:在没有注释测试集的情况下,我们能否评估深度学习模型对任意视觉属性的敏感性?本文论证了Zero-shot模型诊断(ZOOM)不需要测试集也不需要标记的情况下是可能的。为了避免测试集的需要,我们的系统依赖于生成模型和CLIP。关键思想是使用户能够选择一组提示(与问题相关),我们的系统将自动搜索语义反事实图像(即,在二元分类器的情况下翻转预测的合成图像)。我们评估了几个视觉任务(分类,关键点检测和分割)在多个视觉领域,以证明我们的方法的可行性。大量的实验表明,我们的方法是能够产生反事实的图像,并提供灵敏度分析模型诊断,而不需要一个测试集。

英文摘要:

When it comes to deploying deep vision models, the behavior of these systems must be explicable to ensure confidence in their reliability and fairness. A common approach to evaluate deep learning models is to build a labeled test set with attributes of interest and assess how well it performs. However, creating a balanced test set (i.e., one that is uniformly sampled over all the important traits) is often time-consuming, expensive, and prone to mistakes. The question we try to address is: can we evaluate the sensitivity of deep learning models to arbitrary visual attributes without an annotated test set? This paper argues the case that Zero-shot Model Diagnosis (ZOOM) is possible without the need for a test set nor labeling. To avoid the need for test sets, our system relies on a generative model and CLIP. The key idea is enabling the user to select a set of prompts (relevant to the problem) and our system will automatically search for semantic counterfactual images (i.e., synthesized images that flip the prediction in the case of a binary classifier) using the generative model. We evaluate several visual tasks (classification, key-point detection, and segmentation) in multiple visual domains to demonstrate the viability of our methodology. Extensive experiments demonstrate that our method is capable of producing counterfactual images and offering sensitivity analysis for model diagnosis without the need for a test set.

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。

↑