Improved Object Categorization and Detection Using Comparative Object Similarity
- 19 March 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 35 (10), 2442-2453
- https://doi.org/10.1109/tpami.2013.58
Abstract
Due to the intrinsic long-tailed distribution of objects in the real world, we are unlikely to be able to train an object recognizer/detector with many visual examples for each category. We have to share visual knowledge between object categories to enable learning with few or no training examples. In this paper, we show that local object similarity information--statements that pairs of categories are similar or dissimilar--is a very useful cue to tie different categories to each other for effective knowledge transfer. The key insight: Given a set of object categories which are similar and a set of categories which are dissimilar, a good object model should respond more strongly to examples from similar categories than to examples from dissimilar categories. To exploit this category-dependent similarity regularization, we develop a regularized kernel machine algorithm to train kernel classifiers for categories with few or no training examples. We also adapt the state-of-the-art object detector to encode object similarity constraints. Our experiments on hundreds of categories from the Labelme dataset show that our regularized kernel classifiers can make significant improvement on object categorization. We also evaluate the improved object detector on the PASCAL VOC 2007 benchmark dataset.Keywords
This publication has 29 references indexed in Scilit:
- Learning to detect unseen object classes by between-class attribute transferPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Unsupervised learning of visual taxonomiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Learning to Rank for Information RetrievalFoundations and Trends® in Information Retrieval, 2007
- Incremental learning of object detectors using a visual shape alphabetPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene CategoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Cross-Generalization: Learning Novel Classes from a Single Example by Feature ReplacementPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Learning from one example through shared densities on transformsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Classification with nonmetric distances: image retrieval and class representationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- 10.1162/153244303322533214Applied Physics Letters, 2000