Three Things To Know About Deep Metric Learning

Abstract

This paper addresses supervised deep metric learning for open-set image retrieval, focusing on three key aspects: the loss function, mixup regularization, and model initialization. In deep metric learning, optimizing the retrieval evaluation metric, recall@k, via gradient descent is desirable but challenging due to its non-differentiable nature. To overcome this, we propose a differentiable surrogate loss that is computed on large batches, nearly equivalent to the entire training set. This computationally intensive process is made feasible through an implementation that bypasses the GPU memory limitations. Additionally, we introduce an efficient mixup regularization technique that operates on pairwise scalar similarities, effectively increasing the batch size even further. The training process is further enhanced by initializing the vision encoder using foundational models, which are pre-trained on large-scale datasets. Through a systematic study of these components, we demonstrate tha

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypatel2024three

Related papers

• Deep Metric Learning For Computer Vision: A Brief Overview (2023)6.77
• Unbiased Evaluation Of Deep Metric Learning Algorithms (2019)0.00
• Deep Metric Learning Beyond Binary Supervision (2019)14.39
• Classification Is A Strong Baseline For Deep Metric Learning (2018)0.00
• On Background Bias In Deep Metric Learning (2022)0.00
• Directional Statistics-based Deep Metric Learning For Image Classification And Retrieval (2018)13.05
• Deep Metric Learning Assisted By Intra-variance In A Semi-supervised View Of Learning (2023)5.24
• Large-to-small Image Resolution Asymmetry In Deep Metric Learning (2022)9.62