Collaborative error reduction for hierarchical classification
نویسندگان
چکیده
Hierarchical classification (HC) is a popular and efficient way for detecting the semantic concepts from the images. The conventional method always selects the branch with the highest classification response. This branch selection strategy has a risk of propagating classification errors from higher levels of the hierarchy to the lower levels. We argue that the local strategy is too arbitrary, because the candidate nodes are considered individually, which ignores the semantic and context relationships among concepts. In this paper, we first propose a novel method for HC, which is able to utilize the semantic relationship among candidate nodes and their children to recover the responses of unreliable classifiers of the candidate nodes. Thus the error is expected to be reduced by a collaborative branch selection scheme. The approach is further extended to enable multiple branch selection, where other relationships (e.g., contextual information) are incorporated, with the hope of providing the branch selection a more globally valid, semantically and contextually consistent view. An extensive set of experiments on three largescale datasets shows that the proposed methods outperform the conventional HC method, and achieve a satisfactory balance between the effectiveness and efficiency.
منابع مشابه
A classification model for human error in collaborative systems
A Classification Model for Human Error in Collaborative Systems The primary focus of the work reported in this thesis is to investigate and provide a means by which the occurrence of human error in collaborative systems can be better understood. The thesis suggests that much can be gained from looking at human error from a collaborative perspective as opposed to more traditional cognitive and b...
متن کاملSpectral-spatial classification of hyperspectral images by combining hierarchical and marker-based Minimum Spanning Forest algorithms
Many researches have demonstrated that the spatial information can play an important role in the classification of hyperspectral imagery. This study proposes a modified spectral–spatial classification approach for improving the spectral–spatial classification of hyperspectral images. In the proposed method ten spatial/texture features, using mean, standard deviation, contrast, homogeneity, corr...
متن کاملTrajectory tracking of under-actuated nonlinear dynamic robots: Adaptive fuzzy hierarchical terminal sliding-mode control
In recent years, underactuated nonlinear dynamic systems trajectory tracking, such as space robots and manipulators with structural flexibility, has become a major field of interest due to the complexity and high computational load of these systems. Hierarchical sliding mode control has been investigated recently for these systems; however, the instability phenomena will possibly occur, especia...
متن کاملHuman Error Assessment in City Gate Stations of Isfahan Natural Gas Company Using the System for Predictive Error Analysis and Reduction Framework
Introduction: Human factor analysis has been identified as the most common cause of accidents in natural gas transportation and distribution facilities. The occurrence of accidents at these systems, especially gas reduction stations located in residential and industrial areas, has had catastrophic consequences. Therefore, this study aimed at analyzing critical tasks and human error assessment u...
متن کاملCollaborative thesaurus tagging the Wikipedia way
This paper explores the system of categories that is used to classi fy articles in Wikipedia. It is compared to collaborative tagging systems like del.icio.us and to hierarchical classification like the Dewey Decimal Classification (DDC). Specifics and common alities of these systems of subject indexing are exposed. Analysis of structural and statistical properties (descriptors per record, re...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Computer Vision and Image Understanding
دوره 124 شماره
صفحات -
تاریخ انتشار 2014