# Large-scale Bisample Learning on ID Versus Spot Face Recognition

arXiv: https://arxiv.org/abs/1806.03018 · HTML: https://mlsanity.com/paper/1806.03018/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2018.

## Built on by (most cited first, 9 of 9)

- [Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC](https://mlsanity.com/paper/2203.15565/) (2022)
- [Synthetic ID Card Image Generation for Improving Presentation Attack Detection](https://mlsanity.com/paper/2211.00098/) (2022)
- [Searching for Alignment in Face Recognition](https://mlsanity.com/paper/2102.05447/) (2021)
- [Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition](https://mlsanity.com/paper/2103.13851/) (2021)
- [Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning](https://mlsanity.com/paper/2105.04113/) (2021)
- [Multi-modal Extreme Classification](https://mlsanity.com/paper/2309.04961/) (2023)
- [Improving Presentation Attack Detection for ID Cards on Remote Verification Systems](https://mlsanity.com/paper/2301.09542/) (2023)
- [Adaptive Discriminative Regularization for Visual Classification](https://mlsanity.com/paper/2203.00833/) (2022)
- [Privacy-Preserving Model Transcription with Differentially Private Synthetic Distillation](https://mlsanity.com/paper/2601.19090/) (2026)

## Abstract (arXiv)

In real-world face recognition applications, there is a tremendous amount of data with two images for each person. One is an ID photo for face enrollment, and the other is a probe photo captured on spot. Most existing methods are designed for training data with limited breadth (a relatively small number of classes) and sufficient depth (many samples for each class). They would meet great challenges on ID versus Spot (IvS) data, including the under-represented intra-class variations and an excessive demand on computing devices. In this paper, we propose a deep learning based large-scale bisample learning (LBL) method for IvS face recognition. To tackle the bisample problem with only two samples for each class, a classification-verification-classification (CVC) training strategy is proposed to progressively enhance the IvS performance. Besides, a dominant prototype softmax (DP-softmax) is incorporated to make the deep learning scalable on large-scale classes. We conduct LBL on a IvS face dataset with more than two million identities. Experimental results show the proposed method achieves superior performance to previous ones, validating the effectiveness of LBL on IvS face recognition.