On detection of novel categories and subcategories of images using incongruence
On detection of novel categories and subcategories of images using incongruence
复制标题
利用不一致检测图像的新类别和子类别
DOI：
10.1145/2578726.2578769
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Coppi D
中科院分区：
文献类型：
--
作者：
Coppi D
新颖性检测是自主视觉系统开发中的一项重要任务。它的目的是检测样本是否与学习到的模型不一致。在本文中，我们考虑了对象识别问题中的新颖性检测问题，其中对象类集合被分组以形成语义层次。我们遵循这样的想法，在语义层次中，新样本可以被定义为在特定水平上的分类与更一般水平上的分类形成对比的样本。该测量表明样本是否新颖，在这种情况下，它是否可能属于新颖的大类别或新颖的子类别。我们在Caltech256对象数据集和SUN场景数据集的两个分层子集上用不同的分类方案对该方法进行了评估。我们对Weinshall等人进行了改进，并表明可以绕过他们的规范化启发式。我们证明，只要概念分类与视觉层次一致，这种方法就能获得良好的新颖性检测率，但如果不满足这个假设，这种方法往往会失败。
Novelty detection is a crucial task in the development of autonomous vision systems. It aims at detecting if samples do not conform with the learnt models. In this paper, we consider the problem of detecting novelty in object recognition problems in which the set of object classes are grouped to form a semantic hierarchy. We follow the idea that, within a semantic hierarchy, novel samples can be defined as samples whose categorization at a specific level contrasts with the categorization at a more general level. This measure indicates if a sample is novel and, in that case, if it is likely to belong to a novel broad category or to a novel sub-category. We present an evaluation of this approach on two hierarchical subsets of the Caltech256 objects dataset and on the SUN scenes dataset, with different classification schemes. We obtain an improvement over Weinshall et al. and show that it is possible to bypass their normalisation heuristic. We demonstrate that this approach achieves good novelty detection rates as far as the conceptual taxonomy is congruent with the visual hierarchy, but tends to fail if this assumption is not satisfied.