Fine-Grained Visual Comparisons with Local Learning

• Published in: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 192 - 199
• Main Authors: Yu, Aron, Grauman, Kristen
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Computer vision; Conferences; Constants; Euclidean distance; fine-grained; Footwear; Learning; Learning systems; learning-to-rank; local learning; Mathematical models; Pattern recognition; Ranking; relative attributes; Training; Training data; Visual; Visualization
• ISSN: 1063-6919; 1063-6919; 2575-7075
• DOI: 10.1109/CVPR.2014.32

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.