Multi-Similarity Loss With General Pair Weighting for Deep Metric Learning
Authors:
Top Cited Papers
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5017-5025
Abstract
A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad of solutions for deep metric learning. In this pa-per, we provide a general weighting framework for under-standing recent pair-based loss functions. Our contributions are three-fold: (1) we establish a General Pair Weighting (GPW) framework, which casts the sampling problem of deep metric learning into a unified view of pair weighting through gradient analysis, providing a powerful tool for understanding recent pair-based loss functions; (2) we show that with GPW, various existing pair-based methods can be compared and discussed comprehensively, with clear differences and key limitations identified; (3) we propose a new loss called multi-similarity loss (MS loss) under the GPW,which is implemented in two iterative steps (i.e., mining and weighting). This allows it to fully consider three similarities for pair weighting, providing a more principled approach for collecting and weighting informative pairs. Finally, the proposed MS loss obtains new state-of-the-art performance on four image retrieval benchmarks, where it outperforms the most recent approaches, such as ABE[14] and HTL[4], by a large margin, e.g.,60.6%→65.7%on CUB200,and 80.9%→88.0%on In-Shop Clothes Retrieval datasetat Recall@1.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations2016
- Learning by Tracking: Siamese CNN for Robust Target Association2016
- FaceNet: A unified embedding for face recognition and clustering2015
- Learning descriptors for object recognition and 3D pose estimation2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Quadruplet-Wise Image Similarity Learning2013
- 3D Object Representations for Fine-Grained Categorization2013
- Learning a Similarity Metric Discriminatively, with Application to Face Verification2005
- Fisher discriminant analysis with kernels1999
- Similarity Metric Learning for a Variable-Kernel ClassifierNeural Computation, 1995