Markou Markos, Singh Sameer
GORDIOU DESMOU 35, 6045 Larnaca, Cyprus.
IEEE Trans Pattern Anal Mach Intell. 2006 Oct;28(10):1664-77. doi: 10.1109/TPAMI.2006.196.
This paper proposes a new model of "novelty detection" for image sequence analysis using neural networks. This model uses the concept of artificially generated negative data to form closed decision boundaries using a multilayer perceptron. The neural network output is novelty filtered by thresholding the output of multiple networks (one per known class) to which the sample is input and clustered for determining which clusters represent novel classes. After labeling these novel clusters, new networks are trained on this data. We perform experiments with video-based image sequence data containing a number of novel classes. The performance of the novelty filter is evaluated using two performance metrics and we compare our proposed model on the basis of these with five baseline novelty detectors. We also discuss the results of retraining each model after novelty detection. On the basis of Chi-square performance metric, we prove at 5 percent significance level that our optimized novelty detector performs at the same level as an ideal novelty detector that does not make any mistakes.
本文提出了一种用于图像序列分析的新型“新颖性检测”模型，该模型采用神经网络。此模型运用人工生成负数据的概念，利用多层感知器形成封闭的决策边界。通过对样本输入的多个网络（每个已知类别对应一个网络）的输出进行阈值处理，对神经网络输出进行新颖性过滤，并进行聚类以确定哪些聚类代表新颖类别。在标记这些新颖聚类后，基于此数据训练新的网络。我们对包含多个新颖类别的基于视频的图像序列数据进行实验。使用两种性能指标评估新颖性过滤器的性能，并在此基础上将我们提出的模型与五个基线新颖性检测器进行比较。我们还讨论了新颖性检测后重新训练每个模型的结果。基于卡方性能指标，我们在5%的显著性水平上证明，我们优化后的新颖性检测器的性能与不犯任何错误的理想新颖性检测器相当。
