Symbiotic Segmentation and Part Localization for Fine-Grained Categorization
Authors:
- Yuning ChaiYCYuning Chai
- Victor LempitskyVLVictor Lempitsky
- Andrew ZissermanAZAndrew Zisserman
- 1 December 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 321-328
Abstract
We propose a new method for the task of fine-grained visual categorization. The method builds a model of the base-level category that can be fitted to images, producing high-quality foreground segmentation and mid-level part localizations. The model can be learnt from the typical datasets available for fine-grained categorization, where the only annotation provided is a loose bounding box around the instance (e.g. bird) in each image. Both segmentation and part localizations are then used to encode the image content into a highly-discriminative visual signature. The model is symbiotic in that part discovery/localization is helped by segmentation and, conversely, the segmentation is helped by the detection (e.g. part layout). Our model builds on top of the part-based object category detector of Felzenszwalb et al., and also on the powerful Grab Cut segmentation algorithm of Rother et al., and adds a simple spatial saliency coupling between them. In our evaluation, the model improves the categorization accuracy over the state-of-the-art. It also improves over what can be achieved with an analogous system that runs segmentation and part-localization independently.Keywords
This publication has 19 references indexed in Scilit:
- Object detection and segmentation from joint embedding of parts and pixels2011
- Combining randomization and discrimination for fine-grained image categorization2011
- The devil is in the details: an evaluation of recent feature encoding methods2011
- Weakly supervised discriminative localization and classification: a joint learning process2009
- Synergy between Object Recognition and Image Segmentation Using the Expectation-Maximization AlgorithmIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- An empirical study of context in object detection2009
- Automated Flower Classification over a Large Number of Classes2008
- An Exemplar Model for Learning Object Classes2007
- OBJ CUT2005
- Interleaved Object Categorization and Segmentation2003