DAS: Densely-anchored Sampling For Deep Metric Learning

Abstract

Deep Metric Learning (DML) serves to learn an embedding function to project semantically similar data into nearby embedding space and plays a vital role in many applications, such as image retrieval and face recognition. However, the performance of DML methods often highly depends on sampling methods to choose effective data from the embedding space in the training. In practice, the embeddings in the embedding space are obtained by some deep models, where the embedding space is often with barren area due to the absence of training points, resulting in so called "missing embedding" issue. This issue may impair the sample quality, which leads to degenerated DML performance. In this work, we investigate how to alleviate the "missing embedding" issue to improve the sampling quality and achieve effective DML. To this end, we propose a Densely-Anchored Sampling (DAS) scheme that considers the embedding with corresponding data point as "anchor" and exploits the anchor's nearby embedding space

Stats

• citations19
• S2 citations—
• github stars0
• HF likes0
• heat score9.76
• arxiv keyliu2022das

Related papers

• Guided Deep Metric Learning (2022)6.77
• Towards Improved Proxy-based Deep Metric Learning Via Data-augmented Domain Adaptation (2024)6.34
• Improving Deep Metric Learning By Divide And Conquer (2021)8.09
• Revisiting Training Strategies And Generalization Performance In Deep Metric Learning (2020)5.08
• S2SD: Simultaneous Similarity-based Self-distillation For Deep Metric Learning (2020)3.31
• Multi-head Deep Metric Learning Using Global And Local Representations (2021)6.77
• Dynamic Sampling For Deep Metric Learning (2020)5.84
• A Framework To Enhance Generalization Of Deep Metric Learning Methods Using General Discriminative Feature Learning And Class Adversarial Neural Networks (2021)7.50