# Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly

arXiv: https://arxiv.org/abs/1801.04815 · HTML: https://mlsanity.com/paper/1801.04815/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jan 2018.

## Built on by (most cited first, 30 of 40)

- [Hyperbolic Vision Transformers: Combining Improvements in Metric Learning](https://mlsanity.com/paper/2203.10833/) (2022)
- [Training Vision Transformers for Image Retrieval](https://mlsanity.com/paper/2102.05644/) (2021)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [Learning Intra-Batch Connections for Deep Metric Learning](https://mlsanity.com/paper/2102.07753/) (2021)
- [Deep Relational Metric Learning](https://mlsanity.com/paper/2108.10026/) (2021)
- [Embedding Transfer with Label Relaxation for Improved Metric Learning](https://mlsanity.com/paper/2103.14908/) (2021)
- [Learning with Memory-based Virtual Classes for Deep Metric Learning](https://mlsanity.com/paper/2103.16940/) (2021)
- [Integrating Language Guidance into Vision-based Deep Metric Learning](https://mlsanity.com/paper/2203.08543/) (2022)
- [A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning](https://mlsanity.com/paper/2207.03784/) (2022)
- [Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning](https://mlsanity.com/paper/2103.15454/) (2021)
- [Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning](https://mlsanity.com/paper/2107.09562/) (2021)
- [Self-Taught Metric Learning without Labels](https://mlsanity.com/paper/2205.01903/) (2022)
- [Attributable Visual Similarity Learning](https://mlsanity.com/paper/2203.14932/) (2022)
- [Understanding Hyperbolic Metric Learning through Hard Negative Sampling](https://mlsanity.com/paper/2404.15523/) (2024)
- [Contrastive Bayesian Analysis for Deep Metric Learning](https://mlsanity.com/paper/2210.04402/) (2022)
- [Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation](https://mlsanity.com/paper/2411.15763/) (2024)
- [LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning](https://mlsanity.com/paper/2108.09335/) (2021)
- [Introspective Deep Metric Learning](https://mlsanity.com/paper/2309.09982/) (2023)
- [Multi-level Distance Regularization for Deep Metric Learning](https://mlsanity.com/paper/2102.04223/) (2021)
- [The Group Loss++: A deeper look into group loss for deep metric learning](https://mlsanity.com/paper/2204.01509/) (2022)
- [Group Contrastive Self-Supervised Learning on Graphs](https://mlsanity.com/paper/2107.09787/) (2021)
- [Improving Deep Metric Learning by Divide and Conquer](https://mlsanity.com/paper/2109.04003/) (2021)
- [DAS: Densely-Anchored Sampling for Deep Metric Learning](https://mlsanity.com/paper/2208.00119/) (2022)
- [Multi-Head Deep Metric Learning Using Global and Local Representations](https://mlsanity.com/paper/2112.14327/) (2021)
- [Identifying Ambiguous Similarity Conditions via Semantic Matching](https://mlsanity.com/paper/2204.04053/) (2022)
- [Rethinking Deep Contrastive Learning with Embedding Memory](https://mlsanity.com/paper/2103.14003/) (2021)
- [Adaptive neighborhood Metric learning](https://mlsanity.com/paper/2201.08314/) (2022)
- [Ensemble of Loss Functions to Improve Generalizability of Deep Metric Learning methods](https://mlsanity.com/paper/2107.01130/) (2021)
- [Rethinking Batch Sample Relationships for Data Representation: A Batch-Graph Transformer based Approach](https://mlsanity.com/paper/2211.10622/) (2022)
- [Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning](https://mlsanity.com/paper/2211.16264/) (2022)

## Abstract (arXiv)

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 our metric learning method on image retrieval tasks and show that it improves over state-of-the-art methods on the CUB 200-2011, Cars-196, Stanford Online Products, In-Shop Clothes Retrieval and VehicleID datasets.