Generalization In Metric Learning: Should The Embedding Layer Be The Embedding Layer?

Abstract

This work studies deep metric learning under small to medium scale data as we believe that better generalization could be a contributing factor to the improvement of previous fine-grained image retrieval methods; it should be considered when designing future techniques. In particular, we investigate using other layers in a deep metric learning system (besides the embedding layer) for feature extraction and analyze how well they perform on training data and generalize to testing data. From this study, we suggest a new regularization practice where one can add or choose a more optimal layer for feature extraction. State-of-the-art performance is demonstrated on 3 fine-grained image retrieval benchmarks: Cars-196, CUB-200-2011, and Stanford Online Product.

Stats

• citations13
• S2 citations—
• github stars0
• HF likes0
• heat score8.60
• arxiv keyvo2018generalization

Related papers

• Visualizing How Embeddings Generalize (2019)0.00
• Deep Randomized Ensembles For Metric Learning (2018)13.97
• Few-shot Metric Learning: Online Adaptation Of Embedding For Retrieval (2022)8.09
• Divide And Conquer The Embedding Space For Metric Learning (2019)14.39
• A Framework To Enhance Generalization Of Deep Metric Learning Methods Using General Discriminative Feature Learning And Class Adversarial Neural Networks (2021)7.50
• Sharing Matters For Generalization In Deep Metric Learning (2020)8.35
• Learning Intra-batch Connections For Deep Metric Learning (2021)0.00
• Revisiting Training Strategies And Generalization Performance In Deep Metric Learning (2020)5.08