# ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis

arXiv: https://arxiv.org/abs/2004.01113 · HTML: https://mlsanity.com/paper/2004.01113/

## Key facts

- Cited by 107 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2020.

## Built on by (most cited first, 30 of 107)

- [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)
- [Training Vision Transformers for Image Retrieval](https://mlsanity.com/paper/2102.05644/) (2021)
- [Recall@k Surrogate Loss with Large Batches and Similarity Mixup](https://mlsanity.com/paper/2108.11179/) (2021)
- [von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning](https://mlsanity.com/paper/2103.15718/) (2021)
- [Learning Intra-Batch Connections for Deep Metric Learning](https://mlsanity.com/paper/2102.07753/) (2021)
- [Non-isotropy Regularization for Proxy-based Deep Metric Learning](https://mlsanity.com/paper/2203.08547/) (2022)
- [Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs](https://mlsanity.com/paper/2302.02865/) (2023)
- [HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization](https://mlsanity.com/paper/2212.14258/) (2022)
- [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)
- [Robust and Decomposable Average Precision for Image Retrieval](https://mlsanity.com/paper/2110.01445/) (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)
- [Hierarchical Proxy-based Loss for Deep Metric Learning](https://mlsanity.com/paper/2103.13538/) (2021)
- [ERM++: An Improved Baseline for Domain Generalization](https://mlsanity.com/paper/2304.01973/) (2023)
- [CHAMMI: A benchmark for channel-adaptive models in microscopy imaging](https://mlsanity.com/paper/2310.19224/) (2023)
- [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)
- [DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers](https://mlsanity.com/paper/2505.23694/) (2025)
- [Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery](https://mlsanity.com/paper/2307.10943/) (2023)
- [Open Set Synthetic Image Source Attribution](https://mlsanity.com/paper/2308.11557/) (2023)
- [Fine-grained Retrieval Prompt Tuning](https://mlsanity.com/paper/2207.14465/) (2022)
- [Spectral, Probabilistic, and Deep Metric Learning: Tutorial and Survey](https://mlsanity.com/paper/2201.09267/) (2022)
- [Optimization of Rank Losses for Image Retrieval](https://mlsanity.com/paper/2309.08250/) (2023)
- [Understanding Hyperbolic Metric Learning through Hard Negative Sampling](https://mlsanity.com/paper/2404.15523/) (2024)
- [Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers](https://mlsanity.com/paper/2405.16419/) (2024)
- [Bringing Multimodality to Amazon Visual Search System](https://mlsanity.com/paper/2412.13364/) (2024)
- [Effectively Leveraging Attributes for Visual Similarity](https://mlsanity.com/paper/2105.01695/) (2021)

## Abstract (arXiv)

We consider the problem of distance metric learning (DML), where the task is to learn an effective similarity measure between images. We revisit ProxyNCA and incorporate several enhancements. We find that low temperature scaling is a performance-critical component and explain why it works. Besides, we also discover that Global Max Pooling works better in general when compared to Global Average Pooling. Additionally, our proposed fast moving proxies also addresses small gradient issue of proxies, and this component synergizes well with low temperature scaling and Global Max Pooling. Our enhanced model, called ProxyNCA++, achieves a 22.9 percentage point average improvement of Recall@1 across four different zero-shot retrieval datasets compared to the original ProxyNCA algorithm. Furthermore, we achieve state-of-the-art results on the CUB200, Cars196, Sop, and InShop datasets, achieving Recall@1 scores of 72.2, 90.1, 81.4, and 90.9, respectively.