arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.12145cs.LGstat.ML
收藏

基于最大概率定理的分布外检测、推广和鲁棒性三角形

Out of Distribution Detection, Generalization, and Robustness Triangle with Maximum Probability Theorem

Currus AI(Currus人工智能公司);Northwestern University(西北大学)

Amir Emad Marvasti, Ehsan Emad Marvasti, Ulas Bagci

摘要:

最大概率框架是人工智能领域的一个新的理论发展,它以最大概率定理为基础,旨在形式化地定义概率模型,指导目标函数的开发和概率模型的正则化。MPT使用模型对随机变量假设的概率分布来提供模型概率的上限。我们将MPT应用于计算机视觉中具有挑战性的分布外(OOD)检测问题,方法是将MPT作为CNN及其基于能量的变体训练中的正则化方案。我们在1080个具有不同超参数的训练模型上证明了所提出方法的有效性,并得出结论,基于MPT的正则化策略除了在CIFAR10,CIFAR100和MNIST数据集上增强OOD性能外,还稳定和提高了基础模型的泛化和鲁棒性。

英文摘要:

Maximum Probability Framework, powered by Maximum Probability Theorem, is a recent theoretical development in artificial intelligence, aiming to formally define probabilistic models, guiding development of objective functions, and regularization of probabilistic models. MPT uses the probability distribution that the models assume on random variables to provide an upper bound on the probability of the model. We apply MPT to challenging out-of-distribution (OOD) detection problems in computer vision by incorporating MPT as a regularization scheme in the training of CNNs and their energy-based variants. We demonstrate the effectiveness of the proposed method on 1080 trained models, with varying hyperparameters, and conclude that the MPT-based regularization strategy stabilizes and improves the generalization and robustness of base models in addition to enhanced OOD performance on CIFAR10, CIFAR100, and MNIST datasets.

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。

↑