# Learning to Generate Novel Classes for Deep Metric Learning

arXiv: https://arxiv.org/abs/2201.01008 · HTML: https://mlsanity.com/paper/2201.01008/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 4 Jan 2022.

## Builds on (most cited first, 27 of 27)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [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)
- [Learning Generative Models with Sinkhorn Divergences](https://mlsanity.com/paper/1706.00292/) (2017)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [No Fuss Distance Metric Learning using Proxies](https://mlsanity.com/paper/1703.07464/) (2017)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [Beyond triplet loss: a deep quadruplet network for person re-identification](https://mlsanity.com/paper/1704.01719/) (2017)
- [Modulating early visual processing by language](https://mlsanity.com/paper/1707.00683/) (2017)
- [SoftTriple Loss: Deep Metric Learning Without Triplet Sampling](https://mlsanity.com/paper/1909.05235/) (2019)
- [Improving GANs Using Optimal Transport](https://mlsanity.com/paper/1803.05573/) (2018)
- [Smart Mining for Deep Metric Learning](https://mlsanity.com/paper/1704.01285/) (2017)
- [Attention-based Ensemble for Deep Metric Learning](https://mlsanity.com/paper/1804.00382/) (2018)
- [Hardness-Aware Deep Metric Learning](https://mlsanity.com/paper/1903.05503/) (2019)
- [Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly](https://mlsanity.com/paper/1801.04815/) (2018)
- [Deep Metric Learning Beyond Binary Supervision](https://mlsanity.com/paper/1904.09626/) (2019)
- [Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings](https://mlsanity.com/paper/1908.02735/) (2019)
- [Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning](https://mlsanity.com/paper/2003.02546/) (2020)
- [Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning](https://mlsanity.com/paper/2103.15454/) (2021)
- [Symmetrical Synthesis for Deep Metric Learning](https://mlsanity.com/paper/2001.11658/) (2020)
- [Virtual Class Enhanced Discriminative Embedding Learning](https://mlsanity.com/paper/1811.12611/) (2018)

## Built on by (most cited first, 1 of 1)

- [Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning](https://mlsanity.com/paper/2211.16264/) (2022)

## Abstract (arXiv)

Deep metric learning aims to learn an embedding space where the distance between data reflects their class equivalence, even when their classes are unseen during training. However, the limited number of classes available in training precludes generalization of the learned embedding space. Motivated by this, we introduce a new data augmentation approach that synthesizes novel classes and their embedding vectors. Our approach can provide rich semantic information to an embedding model and improve its generalization by augmenting training data with novel classes unavailable in the original data. We implement this idea by learning and exploiting a conditional generative model, which, given a class label and a noise, produces a random embedding vector of the class. Our proposed generator allows the loss to use richer class relations by augmenting realistic and diverse classes, resulting in better generalization to unseen samples. Experimental results on public benchmark datasets demonstrate that our method clearly enhances the performance of proxy-based losses.