# Virtual Class Enhanced Discriminative Embedding Learning

arXiv: https://arxiv.org/abs/1811.12611 · HTML: https://mlsanity.com/paper/1811.12611/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2018.

## Built on by (most cited first, 13 of 13)

- [Regular Polytope Networks](https://mlsanity.com/paper/2103.15632/) (2021)
- [Learning with Memory-based Virtual Classes for Deep Metric Learning](https://mlsanity.com/paper/2103.16940/) (2021)
- [Knowledge Evolution in Neural Networks](https://mlsanity.com/paper/2103.05152/) (2021)
- [Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning](https://mlsanity.com/paper/2103.15454/) (2021)
- [Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting](https://mlsanity.com/paper/2108.08023/) (2021)
- [Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture](https://mlsanity.com/paper/2105.13524/) (2021)
- [MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness](https://mlsanity.com/paper/2312.04960/) (2023)
- [Recent Advances in Large Margin Learning](https://mlsanity.com/paper/2103.13598/) (2021)
- [Deep Metric Learning with Chance Constraints](https://mlsanity.com/paper/2209.09060/) (2022)
- [HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling](https://mlsanity.com/paper/2507.18897/) (2025)
- [BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation](https://mlsanity.com/paper/2511.19394/) (2025)
- [Learning to Generate Novel Classes for Deep Metric Learning](https://mlsanity.com/paper/2201.01008/) (2022)
- [Decoupling Generalizability and Membership Privacy Risks in Neural Networks](https://mlsanity.com/paper/2602.02296/) (2026)

## Abstract (arXiv)

Recently, learning discriminative features to improve the recognition performances gradually becomes the primary goal of deep learning, and numerous remarkable works have emerged. In this paper, we propose a novel yet extremely simple method Virtual Softmax to enhance the discriminative property of learned features by injecting a dynamic virtual negative class into the original softmax. Injecting virtual class aims to enlarge inter-class margin and compress intra-class distribution by strengthening the decision boundary constraint. Although it seems weird to optimize with this additional virtual class, we show that our method derives from an intuitive and clear motivation, and it indeed encourages the features to be more compact and separable. This paper empirically and experimentally demonstrates the superiority of Virtual Softmax, improving the performances on a variety of object classification and face verification tasks.