2022/10/04 by Christopher Liao, Theodoros Tsiligkaridis, Liao, Christopher +3 · 1 citation
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face recognition and analysis #Image Retrieval and Classification Techniques #Machine Learning (cs.LG)
paper · pdf · doi:10.48550/arxiv.2210.01908
openalex publication_date 2022/10/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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