Fine-Grained Visual Comparisons with Local Learning
Authors:
- Aron YuAYAron Yu
- Kristen GraumanKGKristen Grauman
Top Cited Papers
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 192-199
Abstract
Given two images, we want to predict which exhibits a particular visual attribute more than the other-even when the two images are quite similar. Existing relative attribute methods rely on global ranking functions; yet rarely will the visual cues relevant to a comparison be constant for all data, nor will humans' perception of the attribute necessarily permit a global ordering. To address these issues, we propose a local learning approach for fine-grained visual comparisons. Given a novel pair of images, we learn a local ranking model on the fly, using only analogous training comparisons. We show how to identify these analogous pairs using learned metrics. With results on three challenging datasets-including a large newly curated dataset for fine-grained comparisons-our method outperforms stateof-the-art methods for relative attribute prediction.Keywords
This publication has 22 references indexed in Scilit:
- WhittleSearch: Image search with relative attribute feedback2012
- Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance2011
- Hierarchical ranking of facial attributes2011
- Statistical ranking and combinatorial Hodge theoryMathematical Programming, 2010
- Query dependent ranking using K-nearest neighbor2008
- Learning to rank with partially-labeled data2008
- Fast image search for learned metrics2008
- Information-theoretic metric learning2007
- Learning Globally-Consistent Local Distance Functions for Shape-Based Image Retrieval and Classification2007
- Discriminant adaptive nearest neighbor classificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996