论文标题
深度激活的网络比较研究具有新颖对象的可区分性
Network Comparison Study of Deep Activation Feature Discriminability with Novel Objects
论文作者
论文摘要
特征提取一直是计算机视觉字段的关键组成部分。最近，最先进的计算机视觉算法已将深层神经网络（DNN）纳入功能提取角色，从而创建了深度卷积激活功能（DECAF）。 DNN知识领域的可传递性使得对具有新颖对象类的应用，尤其是那些培训数据有限的应用程序，可以广泛使用验证的DNN功能提取。这项研究分析了编码在六个领先的视觉识别DNN体系结构的DePAF空间中的新型对象视觉外观的一般可区分性。这项研究的结果表征了在两个视觉对象跟踪基准数据集的DeCAF对象歧管之间的Mahalanobis距离和余弦相似性。每个对象周围的背景也包括在流形分析中作为对象类，提供了更广泛的新颖类。这项研究发现，不同的网络体系结构导致不同的网络功能重点是在网络选择过程中必须考虑的。这些结果是由fot2015和UAV123基准数据集产生的；但是，所提出的方法可以应用于有效比较任何标记的视觉数据集的估计网络性能特征。
Feature extraction has always been a critical component of the computer vision field. More recently, state-of-the-art computer visions algorithms have incorporated Deep Neural Networks (DNN) in feature extracting roles, creating Deep Convolutional Activation Features (DeCAF). The transferability of DNN knowledge domains has enabled the wide use of pretrained DNN feature extraction for applications with novel object classes, especially those with limited training data. This study analyzes the general discriminability of novel object visual appearances encoded into the DeCAF space of six of the leading visual recognition DNN architectures. The results of this study characterize the Mahalanobis distances and cosine similarities between DeCAF object manifolds across two visual object tracking benchmark data sets. The backgrounds surrounding each object are also included as an object classes in the manifold analysis, providing a wider range of novel classes. This study found that different network architectures led to different network feature focuses that must to be considered in the network selection process. These results are generated from the VOT2015 and UAV123 benchmark data sets; however, the proposed methods can be applied to efficiently compare estimated network performance characteristics for any labeled visual data set.
