Supervised Metric Learning To Rank For Retrieval Via Contextual Similarity Optimization

Abstract

There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongly overfit semantically inconsistent labels and require a large amount of data. To address these shortcomings, we propose a new metric learning method, called contextual loss, which optimizes contextual similarity in addition to cosine similarity. Our contextual loss implicitly enforces semantic consistency among neighbors while converging to the correct ranking. We empirically show that the proposed loss is more robust to label noise, and is less prone to overfitting even when a large portion of train data is withheld. Extensive experiments demonstrate that our method achieves a new state-of-the-art across four image retrieval benchmarks and multiple different evaluation settings. Code is available at: https://github.com/Chris210634/metric-learning-using-contextual-similarity

Stats

• citations0
• S2 citations—
• github stars20
• HF likes0
• heat score2.64
• arxiv keyliao2022supervised

Code

• Chris210634/metric-learning-using-contextual-similarity—

Related papers

• Deep Metric Learning Using Similarities From Nonlinear Rank Approximations (2019)2.26
• Three Things To Know About Deep Metric Learning (2024)0.00
• Variance & Greediness: A Comparative Study Of Metric-learning Losses (2026)0.00
• Deep Metric Learning Beyond Binary Supervision (2019)14.39
• Hyp\(^2\) Loss: Beyond Hypersphere Metric Space For Multi-label Image Retrieval (2022)13.32
• Sharing Matters For Generalization In Deep Metric Learning (2020)8.35
• Few-shot Metric Learning: Online Adaptation Of Embedding For Retrieval (2022)8.09
• Deep Metric Learning Assisted By Intra-variance In A Semi-supervised View Of Learning (2023)5.24