# Proxy Anchor Loss for Deep Metric Learning

arXiv: https://arxiv.org/abs/2003.13911 · HTML: https://mlsanity.com/paper/2003.13911/

## Key facts

- Cited by 195 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2020.

## Built on by (most cited first, 30 of 195)

- [ABO: Dataset and Benchmarks for Real-World 3D Object Understanding](https://mlsanity.com/paper/2110.06199/) (2021)
- [How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?](https://mlsanity.com/paper/2203.04450/) (2022)
- [Hyperbolic Vision Transformers: Combining Improvements in Metric Learning](https://mlsanity.com/paper/2203.10833/) (2022)
- [High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning](https://mlsanity.com/paper/2106.03609/) (2021)
- [GeneCIS: A Benchmark for General Conditional Image Similarity](https://mlsanity.com/paper/2306.07969/) (2023)
- [Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training](https://mlsanity.com/paper/2203.00972/) (2022)
- [Learning Intra-Batch Connections for Deep Metric Learning](https://mlsanity.com/paper/2102.07753/) (2021)
- [SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery](https://mlsanity.com/paper/2408.14371/) (2024)
- [Non-isotropy Regularization for Proxy-based Deep Metric Learning](https://mlsanity.com/paper/2203.08547/) (2022)
- [Birds of a Feather: Capturing Avian Shape Models from Images](https://mlsanity.com/paper/2105.09396/) (2021)
- [Towards Interpretable Deep Metric Learning with Structural Matching](https://mlsanity.com/paper/2108.05889/) (2021)
- [HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization](https://mlsanity.com/paper/2212.14258/) (2022)
- [A Deep Metric Learning Approach to Account Linking](https://mlsanity.com/paper/2105.07263/) (2021)
- [Noise-resistant Deep Metric Learning with Ranking-based Instance Selection](https://mlsanity.com/paper/2103.16047/) (2021)
- [It Takes Two to Tango: Mixup for Deep Metric Learning](https://mlsanity.com/paper/2106.04990/) (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)
- [Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2104.01286/) (2021)
- [Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem](https://mlsanity.com/paper/2210.00411/) (2022)
- [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)
- [Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards](https://mlsanity.com/paper/2405.13459/) (2024)
- [Hierarchical Proxy-based Loss for Deep Metric Learning](https://mlsanity.com/paper/2103.13538/) (2021)
- [Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual Styles](https://mlsanity.com/paper/2109.03158/) (2021)
- [From Global to Local: Multi-scale Out-of-distribution Detection](https://mlsanity.com/paper/2308.10239/) (2023)
- [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)
- [Continual Learning for Visual Search with Backward Consistent Feature Embedding](https://mlsanity.com/paper/2205.13384/) (2022)
- [Utilizing Expert Features for Contrastive Learning of Time-Series Representations](https://mlsanity.com/paper/2206.11517/) (2022)

## Abstract (arXiv)

Existing metric learning losses can be categorized into two classes: pair-based and proxy-based losses. The former class can leverage fine-grained semantic relations between data points, but slows convergence in general due to its high training complexity. In contrast, the latter class enables fast and reliable convergence, but cannot consider the rich data-to-data relations. This paper presents a new proxy-based loss that takes advantages of both pair- and proxy-based methods and overcomes their limitations. Thanks to the use of proxies, our loss boosts the speed of convergence and is robust against noisy labels and outliers. At the same time, it allows embedding vectors of data to interact with each other in its gradients to exploit data-to-data relations. Our method is evaluated on four public benchmarks, where a standard network trained with our loss achieves state-of-the-art performance and most quickly converges.