Contextualizing Object Detection and Classification
- 28 July 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 37 (1), 13-27
- https://doi.org/10.1109/tpami.2014.2343217
Abstract
We investigate how to iteratively and mutually boost object classification and detection performance by taking the outputs from one task as the context of the other one. While context models have been quite popular, previous works mainly concentrate on co-occurrence relationship within classes and few of them focus on contextualization from a top-down perspective, i.e. high-level task context. In this paper, our system adopts a new method for adaptive context modeling and iterative boosting. First, the contextualized support vector machine (Context-SVM) is proposed, where the context takes the role of dynamically adjusting the classification score based on the sample ambiguity, and thus the context-adaptive classifier is achieved. Then, an iterative training procedure is presented. In each step, Context-SVM, associated with the output context from one task (object classification or detection), is instantiated to boost the performance for the other task, whose augmented outputs are then further used to improve the former task by Context-SVM. The proposed solution is evaluated on the object classification and detection tasks of PASCAL Visual Object Classes Challenge (VOC) 2007, 2010 and SUN09 data sets, and achieves the state-of-the-art performance.This publication has 30 references indexed in Scilit:
- Towards good practice in large-scale learning for image classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Contextualizing object detection and classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Hierarchical semantic indexing for large scale image retrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Discriminative models for multi-class object layoutPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Evaluating Color Descriptors for Object and Scene RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- LabelMe: A Database and Web-Based Tool for Image AnnotationInternational Journal of Computer Vision, 2007
- A Critical View of ContextInternational Journal of Computer Vision, 2006
- Contextual Priming for Object DetectionInternational Journal of Computer Vision, 2003
- A Generalized Representer TheoremLecture Notes in Computer Science, 2001
- Stacked generalizationNeural Networks, 1992