# Generalizable Embeddings with Cross-batch Metric Learning

arXiv: https://arxiv.org/abs/2307.07620 · HTML: https://mlsanity.com/paper/2307.07620/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 14 Jul 2023.

## Builds on (most cited first, 21 of 21)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning](https://mlsanity.com/paper/1904.06627/) (2019)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis](https://mlsanity.com/paper/2004.01113/) (2020)
- [Interpreting Deep Visual Representations via Network Dissection](https://mlsanity.com/paper/1711.05611/) (2017)
- [Revisiting Training Strategies and Generalization Performance in Deep Metric Learning](https://mlsanity.com/paper/2002.08473/) (2020)
- [Recall@k Surrogate Loss with Large Batches and Similarity Mixup](https://mlsanity.com/paper/2108.11179/) (2021)
- [MIC: Mining Interclass Characteristics for Improved Metric Learning](https://mlsanity.com/paper/1909.11574/) (2019)
- [DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning](https://mlsanity.com/paper/2004.13458/) (2020)
- [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)
- [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)
- [S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning](https://mlsanity.com/paper/2009.08348/) (2020)
- [Deep Metric Learning with Alternating Projections onto Feasible Sets](https://mlsanity.com/paper/1907.07585/) (2019)
- [Deep Metric Learning with Chance Constraints](https://mlsanity.com/paper/2209.09060/) (2022)

## Built on by (most cited first, 2 of 2)

- [Generalized Sum Pooling for Metric Learning](https://mlsanity.com/paper/2308.09228/) (2023)
- [Knowledge Distillation Layer that Lets the Student Decide](https://mlsanity.com/paper/2309.02843/) (2023)

## Abstract (arXiv)

Global average pooling (GAP) is a popular component in deep metric learning (DML) for aggregating features. Its effectiveness is often attributed to treating each feature vector as a distinct semantic entity and GAP as a combination of them. Albeit substantiated, such an explanation's algorithmic implications to learn generalizable entities to represent unseen classes, a crucial DML goal, remain unclear. To address this, we formulate GAP as a convex combination of learnable prototypes. We then show that the prototype learning can be expressed as a recursive process fitting a linear predictor to a batch of samples. Building on that perspective, we consider two batches of disjoint classes at each iteration and regularize the learning by expressing the samples of a batch with the prototypes that are fitted to the other batch. We validate our approach on 4 popular DML benchmarks.