Similarity Comparisons for Interactive Fine-Grained Categorization
Authors:
- Catherine WahCWCatherine Wah
- Grant Van HornGHGrant Van Horn
- Steve BransonSBSteve Branson
- Subhransu MajiSMSubhransu Maji
- Pietro PeronaPPPietro Perona
- Serge BelongieSBSerge Belongie
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 859-866
Abstract
Current human-in-the-loop fine-grained visual categorization systems depend on a predefined vocabulary of attributes and parts, usually determined by experts. In this work, we move away from that expert-driven and attribute-centric paradigm and present a novel interactive classification system that incorporates computer vision and perceptual similarity metrics in a unified framework. At test time, users are asked to judge relative similarity between a query image and various sets of images, these general queries do not require expert-defined terminology and are applicable to other domains and basic-level categories, enabling a flexible, efficient, and scalable system for fine-grained categorization with humans in the loop. Our system outperforms existing state-of-the-art systems for relevance feedback-based image retrieval as well as interactive classification, resulting in a reduction of up to 43% in the average number of questions needed to correctly classify an image.Keywords
This publication has 18 references indexed in Scilit:
- Stochastic triplet embedding2012
- Multiclass recognition and part localization with humans in the loop2011
- Actively selecting annotations among objects and attributes2011
- Attribute-centric recognition for cross-category generalization2010
- Attribute and simile classifiers for face verification2009
- Describing objects by their attributes2009
- Learning to detect unseen object classes by between-class attribute transfer2009
- A Statistical Framework for Image Category Search from a Mental PictureIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Interactive Search for Image Categories by Mental Matching2007
- Features of similarity.Psychological Review, 1977