# Semi-Siamese Training for Shallow Face Learning

arXiv: https://arxiv.org/abs/2007.08398 · HTML: https://mlsanity.com/paper/2007.08398/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2020.

## Built on by (most cited first, 19 of 19)

- [Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC](https://mlsanity.com/paper/2203.15565/) (2022)
- [FaceX-Zoo: A PyTorch Toolbox for Face Recognition](https://mlsanity.com/paper/2101.04407/) (2021)
- [WebFace260M: A Benchmark for Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2204.10149/) (2022)
- [Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments](https://mlsanity.com/paper/2105.08149/) (2021)
- [A Quality Aware Sample-to-Sample Comparison for Face Recognition](https://mlsanity.com/paper/2306.04000/) (2023)
- [Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation](https://mlsanity.com/paper/2304.10066/) (2023)
- [Dynamic Class Queue for Large Scale Face Recognition In the Wild](https://mlsanity.com/paper/2105.11113/) (2021)
- [An Efficient Training Approach for Very Large Scale Face Recognition](https://mlsanity.com/paper/2105.10375/) (2021)
- [Semi-Siamese Bi-encoder Neural Ranking Model Using Lightweight Fine-Tuning](https://mlsanity.com/paper/2110.14943/) (2021)
- [Towards NIR-VIS Masked Face Recognition](https://mlsanity.com/paper/2104.06761/) (2021)
- [Prototype Memory for Large-scale Face Representation Learning](https://mlsanity.com/paper/2105.02103/) (2021)
- [Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning](https://mlsanity.com/paper/2105.04113/) (2021)
- [Information Maximization for Extreme Pose Face Recognition](https://mlsanity.com/paper/2209.03456/) (2022)
- [Rethinking Robust Representation Learning Under Fine-grained Noisy Faces](https://mlsanity.com/paper/2208.04352/) (2022)
- [A Survey of Face Recognition](https://mlsanity.com/paper/2212.13038/) (2022)
- [CCFace: Classification Consistency for Low-Resolution Face Recognition](https://mlsanity.com/paper/2308.09230/) (2023)
- [Learning Unified Representations for Multi-Resolution Face Recognition](https://mlsanity.com/paper/2310.09563/) (2023)
- [Improved Face Representation via Joint Label Classification and Supervised Contrastive Clustering](https://mlsanity.com/paper/2312.04029/) (2023)
- [AttFC: Attention Fully-Connected Layer for Large-Scale Face Recognition with One GPU](https://mlsanity.com/paper/2503.06839/) (2025)

## Abstract (arXiv)

Most existing public face datasets, such as MS-Celeb-1M and VGGFace2, provide abundant information in both breadth (large number of IDs) and depth (sufficient number of samples) for training. However, in many real-world scenarios of face recognition, the training dataset is limited in depth, i.e. only two face images are available for each ID. textitWe define this situation as Shallow Face Learning, and find it problematic with existing training methods. Unlike deep face data, the shallow face data lacks intra-class diversity. As such, it can lead to collapse of feature dimension and consequently the learned network can easily suffer from degeneration and over-fitting in the collapsed dimension. In this paper, we aim to address the problem by introducing a novel training method named Semi-Siamese Training (SST). A pair of Semi-Siamese networks constitute the forward propagation structure, and the training loss is computed with an updating gallery queue, conducting effective optimization on shallow training data. Our method is developed without extra-dependency, thus can be flexibly integrated with the existing loss functions and network architectures. Extensive experiments on various benchmarks of face recognition show the proposed method significantly improves the training, not only in shallow face learning, but also for conventional deep face data.