Adaptive Cross Batch Normalization For Metric Learning

Abstract

Metric learning is a fundamental problem in computer vision whereby a model is trained to learn a semantically useful embedding space via ranking losses. Traditionally, the effectiveness of a ranking loss depends on the minibatch size, and is, therefore, inherently limited by the memory constraints of the underlying hardware. While simply accumulating the embeddings across minibatches has proved useful (Wang et al. [2020]), we show that it is equally important to ensure that the accumulated embeddings are up to date. In particular, it is necessary to circumvent the representational drift between the accumulated embeddings and the feature embeddings at the current training iteration as the learnable parameters are being updated. In this paper, we model representational drift as distribution misalignment and tackle it using moment matching. The result is a simple method for updating the stored embeddings to match the first and second moments of the current embeddings at each training ite

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyajanthan2023adaptive

Related papers

• Learning Intra-batch Connections For Deep Metric Learning (2021)0.00
• Cross-batch Memory For Embedding Learning (2019)22.13
• Few-shot Metric Learning: Online Adaptation Of Embedding For Retrieval (2022)8.09
• Rethinking Preventing Class-collapsing In Metric Learning With Margin-based Losses (2020)9.23
• Three Things To Know About Deep Metric Learning (2024)0.00
• Deep Metric Learning For Computer Vision: A Brief Overview (2023)6.77
• Learning A Metric Embedding For Face Recognition Using The Multibatch Method (2016)0.00
• Deep Metric Learning Assisted By Intra-variance In A Semi-supervised View Of Learning (2023)5.24