对抗制
新颖性
人工智能
新知识检测
计算机科学
模式识别(心理学)
心理学
社会心理学
作者
Muhammad Asad,Ihsan Ullah,Ganesh Sistu,Michael G. Madden
出处
期刊:Cornell University - arXiv
日期:2024-04-05
标识
DOI:10.48550/arxiv.2404.04456
摘要
In novelty detection, the goal is to decide if a new data point should be categorized as an inlier or an outlier, given a training dataset that primarily captures the inlier distribution. Recent approaches typically use deep encoder and decoder network frameworks to derive a reconstruction error, and employ this error either to determine a novelty score, or as the basis for a one-class classifier. In this research, we use a similar framework but with a lightweight deep network, and we adopt a probabilistic score with reconstruction error. Our methodology calculates the probability of whether the sample comes from the inlier distribution or not. This work makes two key contributions. The first is that we compute the novelty probability by linearizing the manifold that holds the structure of the inlier distribution. This allows us to interpret how the probability is distributed and can be determined in relation to the local coordinates of the manifold tangent space. The second contribution is that we improve the training protocol for the network. Our results indicate that our approach is effective at learning the target class, and it outperforms recent state-of-the-art methods on several benchmark datasets.
科研通智能强力驱动
Strongly Powered by AbleSci AI