# Asymmetric metric learning for knowledge transfer

arXiv: https://arxiv.org/abs/2006.16331 · HTML: https://mlsanity.com/paper/2006.16331/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2020.

## Built on by (most cited first, 29 of 29)

- [Forward Compatible Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2203.06953/) (2022)
- [Class-Balanced Distillation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2104.05279/) (2021)
- [Compatibility-aware Heterogeneous Visual Search](https://mlsanity.com/paper/2105.06047/) (2021)
- [Towards Universal Backward-Compatible Representation Learning](https://mlsanity.com/paper/2203.01583/) (2022)
- [Forward Compatible Training for Large-Scale Embedding Retrieval Systems](https://mlsanity.com/paper/2112.02805/) (2021)
- [AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval](https://mlsanity.com/paper/2408.03282/) (2024)
- [CoReS: Compatible Representations via Stationarity](https://mlsanity.com/paper/2111.07632/) (2021)
- [Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval](https://mlsanity.com/paper/2403.01431/) (2024)
- [Generalized Knowledge Distillation via Relationship Matching](https://mlsanity.com/paper/2205.01915/) (2022)
- [Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning](https://mlsanity.com/paper/2108.02959/) (2021)
- [Privacy-Preserving Model Upgrades with Bidirectional Compatible Training in Image Retrieval](https://mlsanity.com/paper/2204.13919/) (2022)
- [Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation](https://mlsanity.com/paper/2108.03372/) (2021)
- [boldsymbolλ-Orthogonality Regularization for Compatible Representation Learning](https://mlsanity.com/paper/2509.16664/) (2025)
- [Hot-Refresh Model Upgrades with Regression-Alleviating Compatible Training in Image Retrieval](https://mlsanity.com/paper/2201.09724/) (2022)
- [FastFill: Efficient Compatible Model Update](https://mlsanity.com/paper/2303.04766/) (2023)
- [CL2R: Compatible Lifelong Learning Representations](https://mlsanity.com/paper/2211.09032/) (2022)
- [Binary Embedding-based Retrieval at Tencent](https://mlsanity.com/paper/2302.08714/) (2023)
- [Darwinian Model Upgrades: Model Evolving with Selective Compatibility](https://mlsanity.com/paper/2210.06954/) (2022)
- [Large-to-small Image Resolution Asymmetry in Deep Metric Learning](https://mlsanity.com/paper/2210.05463/) (2022)
- [Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer](https://mlsanity.com/paper/2408.08793/) (2024)
- [Asymmetric Image Retrieval with Cross Model Compatible Ensembles](https://mlsanity.com/paper/2303.17531/) (2023)
- [Structure Similarity Preservation Learning for Asymmetric Image Retrieval](https://mlsanity.com/paper/2403.00648/) (2024)
- [Towards Test-time Efficient Visual Place Recognition via Asymmetric Query Processing](https://mlsanity.com/paper/2512.13055/) (2025)
- [Selective Cross-Task Distillation](https://mlsanity.com/paper/2204.11526/) (2022)
- [Switchable Representation Learning Framework with Self-compatibility](https://mlsanity.com/paper/2206.08289/) (2022)
- [Propheter: Prophetic Teacher Guided Long-Tailed Distribution Learning](https://mlsanity.com/paper/2304.04135/) (2023)
- [Learning Unified Representations for Multi-Resolution Face Recognition](https://mlsanity.com/paper/2310.09563/) (2023)
- [Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval](https://mlsanity.com/paper/2504.11879/) (2025)
- [AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localization](https://mlsanity.com/paper/2604.09445/) (2026)

## Abstract (arXiv)

Knowledge transfer from large teacher models to smaller student models has recently been studied for metric learning, focusing on fine-grained classification. In this work, focusing on instance-level image retrieval, we study an asymmetric testing task, where the database is represented by the teacher and queries by the student. Inspired by this task, we introduce asymmetric metric learning, a novel paradigm of using asymmetric representations at training. This acts as a simple combination of knowledge transfer with the original metric learning task. We systematically evaluate different teacher and student models, metric learning and knowledge transfer loss functions on the new asymmetric testing as well as the standard symmetric testing task, where database and queries are represented by the same model. We find that plain regression is surprisingly effective compared to more complex knowledge transfer mechanisms, working best in asymmetric testing. Interestingly, our asymmetric metric learning approach works best in symmetric testing, allowing the student to even outperform the teacher.