Deep Metric Learning With BIER: Boosting Independent Embeddings Robustly

Abstract

Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of embeddings. In this work, we show how to improve the robustness of such embeddings by exploiting the independence within ensembles. To this end, we divide the last embedding layer of a deep network into an embedding ensemble and formulate training this ensemble as an online gradient boosting problem. Each learner receives a reweighted training sample from the previous learners. Further, we propose two loss functions which increase the diversity in our ensemble. These loss functions can be applied either for weight initialization or during training. Together, our contributions leverage large embedding sizes more effectively by significantly reducing correlation of the embedding and consequently increase retrieval accuracy of the embedding. Our method works with any differentiable loss function and does not introduce any additional parameters during test time. We evaluate o

Stats

• citations86
• S2 citations—
• github stars0
• HF likes0
• heat score14.55
• arxiv keyopitz2018deep

Related papers

• Deep Randomized Ensembles For Metric Learning (2018)13.97
• Attention-based Ensemble For Deep Metric Learning (2018)15.90
• Deep Metric Learning Assisted By Intra-variance In A Semi-supervised View Of Learning (2023)5.24
• IDEAL: Independent Domain Embedding Augmentation Learning (2021)0.00
• Ensemble Of Loss Functions To Improve Generalizability Of Deep Metric Learning Methods (2021)7.16
• The Group Loss For Deep Metric Learning (2019)11.39
• Learning Deep Optimal Embeddings With Sinkhorn Divergences (2022)0.00
• Learning Intra-batch Connections For Deep Metric Learning (2021)0.00