Nonparametric Part Transfer for Fine-Grained Recognition
- 1 June 2014
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2489-2496
- https://doi.org/10.1109/cvpr.2014.319
Abstract
In the following paper, we present an approach for fine-grained recognition based on a new part detection method. In particular, we propose a nonparametric label transfer technique which transfers part constellations from objects with similar global shapes. The possibility for transferring part annotations to unseen images allows for coping with a high degree of pose and view variations in scenarios where traditional detection models (such as deformable part models) fail. Our approach is especially valuable for fine-grained recognition scenarios where intraclass variations are extremely high, and precisely localized features need to be extracted. Furthermore, we show the importance of carefully designed visual extraction strategies, such as combination of complementary feature types and iterative image segmentation, and the resulting impact on the recognition performance. In experiments, our simple yet powerful approach achieves 35.9% and 57.8% accuracy on the CUB-2010 and 2011 bird datasets, which is the current best performance for these benchmarks.Keywords
This publication has 24 references indexed in Scilit:
- Deformable Part Descriptors for Fine-Grained Recognition and Attribute PredictionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Fine-Grained Categorization by AlignmentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Bird Part Localization Using Exemplar-Based Models with Enforced Pose and Subcategory ConsistencyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Labeling Examples That Matter: Relevance-Based Active Learning with Gaussian ProcessesLecture Notes in Computer Science, 2013
- Efficient Additive Kernels via Explicit Feature MapsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Multiclass recognition and part localization with humans in the loopPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Nonparametric Scene Parsing via Label TransferIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Multiple kernels for object detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009