Distributionally Robust Optimization for Deep Kernel Multiple Instance Learning-猫眼课题宝

DOI：

发表时间：

2021

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Hitesh Sapkota;Yiming Ying;F. Chen;Qi Yu

多实例学习（MIL）为许多现实世界的问题提供了一个有前途的解决方案，其中标签仅在袋级可用，但由于标签成本高而缺少实例。高斯过程（Gaussian Processes，GP）作为一种功能强大的贝叶斯非参数模型，已从经典的监督学习扩展到MIL环境，旨在仅使用袋级标签从阳性（或阴性）袋中识别最可能的阳性（或最不可能的阴性）实例。然而，只关注袋子中的单个实例会使模型对离群值或多模态场景的鲁棒性降低，其中单个袋子包含一组不同的正实例。我们提出了一个通用的GP混合框架，同时考虑多个实例，通过一个潜在的混合模型。通过添加top-k约束，该框架相当于选择top-k最积极的实例，使其对离群值和多模态场景更具鲁棒性。我们进一步引入了分布鲁棒优化（DRO）约束，该约束消除了指定固定k值的限制。为了确保对高维数据的预测能力（例如，视频和图像），我们通过使用深度神经网络来学习自适应基函数，从而使用固定的基函数来增强GP内核，以便可以准确地捕获高维数据的协方差结构。在高挑战性的真实视频异常检测任务上进行了实验，以证明所提出的模型的有效性。2021年第24届人工智能与统计国际会议（AISTATS）论文集，美国加州圣地亚哥。130.第130章.版权所有2021由作者（S）。* 通讯作者

Multiple Instance Learning (MIL) provides a promising solution to many real-world problems, where labels are only available at the bag level but missing for instances due to a high labeling cost. As a powerful Bayesian non-parametric model, Gaussian Processes (GP) have been extended from classical supervised learning to MIL settings, aiming to identify the most likely positive (or least negative) instance from a positive (or negative) bag using only the bag-level labels. However, solely focusing on a single instance in a bag makes the model less robust to outliers or multi-modal scenarios, where a single bag contains a diverse set of positive instances. We propose a general GP mixture framework that simultaneously considers multiple instances through a latent mixture model. By adding a top-k constraint, the framework is equivalent to choosing the top-k most positive instances, making it more robust to outliers and multimodal scenarios. We further introduce a Distributionally Robust Optimization (DRO) constraint that removes the limitation of specifying a fix k value. To ensure the prediction power over high-dimensional data (e.g., videos and images) that are common in MIL, we augment the GP kernel with fixed basis functions by using a deep neural network to learn adaptive basis functions so that the covariance structure of high-dimensional data can be accurately captured. Experiments are conducted on highly challenging real-world video anomaly detection tasks to demonstrate the effectiveness of the proposed model. Proceedings of the 24 International Conference on Artificial Intelligence and Statistics (AISTATS) 2021, San Diego, California, USA. PMLR: Volume 130. Copyright 2021 by the author(s). * Corresponding author

Distributionally Robust Optimization for Deep Kernel Multiple Instance Learning

文献摘要

被引文献

相似文献