# SubFace: Learning with Softmax Approximation for Face Recognition

arXiv: https://arxiv.org/abs/2208.11483 · HTML: https://mlsanity.com/paper/2208.11483/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 46 references that are in the map.
- First posted on arXiv 24 Aug 2022.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [The MegaFace Benchmark: 1 Million Faces for Recognition at Scale](https://mlsanity.com/paper/1512.00596/) (2015)
- [MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices](https://mlsanity.com/paper/1804.07573/) (2018)
- [Deep Pyramidal Residual Networks](https://mlsanity.com/paper/1610.02915/) (2016)
- [SoftTriple Loss: Deep Metric Learning Without Triplet Sampling](https://mlsanity.com/paper/1909.05235/) (2019)
- [Partial FC: Training 10 Million Identities on a Single Machine](https://mlsanity.com/paper/2010.05222/) (2020)
- [Deep Learning Face Representation by Joint Identification-Verification](https://mlsanity.com/paper/1406.4773/) (2014)
- [GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognition](https://mlsanity.com/paper/2005.10497/) (2020)
- [Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification](https://mlsanity.com/paper/2109.10498/) (2021)
- [Robust Face Recognition via Multimodal Deep Face Representation](https://mlsanity.com/paper/1509.00244/) (2015)
- [Sparsifying Neural Network Connections for Face Recognition](https://mlsanity.com/paper/1512.01891/) (2015)
- [Triplet Probabilistic Embedding for Face Verification and Clustering](https://mlsanity.com/paper/1604.05417/) (2016)
- [Learning from Self-Discrepancy via Multiple Co-teaching for Cross-Domain Person Re-Identification](https://mlsanity.com/paper/2104.02265/) (2021)

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

- [Unicom: Universal and Compact Representation Learning for Image Retrieval](https://mlsanity.com/paper/2304.05884/) (2023)

## Abstract (arXiv)

The softmax-based loss functions and its variants (e.g., cosface, sphereface, and arcface) significantly improve the face recognition performance in wild unconstrained scenes. A common practice of these algorithms is to perform optimizations on the multiplication between the embedding features and the linear transformation matrix. However in most cases, the dimension of embedding features is given based on traditional design experience, and there is less-studied on improving performance using the feature itself when giving a fixed size. To address this challenge, this paper presents a softmax approximation method called SubFace, which employs the subspace feature to promote the performance of face recognition. Specifically, we dynamically select the non-overlapping subspace features in each batch during training, and then use the subspace features to approximate full-feature among softmax-based loss, so the discriminability of the deep model can be significantly enhanced for face recognition. Comprehensive experiments conducted on benchmark datasets demonstrate that our method can significantly improve the performance of vanilla CNN baseline, which strongly proves the effectiveness of subspace strategy with the margin-based loss.