# DAIL: Dataset-Aware and Invariant Learning for Face Recognition

arXiv: https://arxiv.org/abs/2101.05419 · HTML: https://mlsanity.com/paper/2101.05419/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 56 references that are in the map.
- First posted on arXiv 14 Jan 2021.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [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)
- [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)
- [The MegaFace Benchmark: 1 Million Faces for Recognition at Scale](https://mlsanity.com/paper/1512.00596/) (2015)
- [Deep Learning Face Representation by Joint Identification-Verification](https://mlsanity.com/paper/1406.4773/) (2014)
- [A Light CNN for Deep Face Representation with Noisy Labels](https://mlsanity.com/paper/1511.02683/) (2015)
- [Range Loss for Deep Face Recognition with Long-tail](https://mlsanity.com/paper/1611.08976/) (2016)
- [The Devil of Face Recognition is in the Noise](https://mlsanity.com/paper/1807.11649/) (2018)
- [UMDFaces: An Annotated Face Dataset for Training Deep Networks](https://mlsanity.com/paper/1611.01484/) (2016)
- [Rethinking Feature Distribution for Loss Functions in Image Classification](https://mlsanity.com/paper/1803.02988/) (2018)
- [Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation](https://mlsanity.com/paper/1708.03769/) (2017)
- [Noise-Tolerant Paradigm for Training Face Recognition CNNs](https://mlsanity.com/paper/1903.10357/) (2019)
- [Targeting Ultimate Accuracy: Face Recognition via Deep Embedding](https://mlsanity.com/paper/1506.07310/) (2015)
- [Template Adaptation for Face Verification and Identification](https://mlsanity.com/paper/1603.03958/) (2016)
- [Disentangled Variational Representation for Heterogeneous Face Recognition](https://mlsanity.com/paper/1809.01936/) (2018)
- [Adversarial Discriminative Heterogeneous Face Recognition](https://mlsanity.com/paper/1709.03675/) (2017)
- [SSPP-DAN: Deep Domain Adaptation Network for Face Recognition with Single Sample Per Person](https://mlsanity.com/paper/1702.04069/) (2017)

## Built on by (most cited first, 3 of 3)

- [Prototype Memory for Large-scale Face Representation Learning](https://mlsanity.com/paper/2105.02103/) (2021)
- [Disjoint Contrastive Regression Learning for Multi-Sourced Annotations](https://mlsanity.com/paper/2112.15411/) (2021)
- [FaceFusion: Exploiting Full Spectrum of Multiple Datasets](https://mlsanity.com/paper/2305.14601/) (2023)

## Abstract (arXiv)

To achieve good performance in face recognition, a large scale training dataset is usually required. A simple yet effective way to improve recognition performance is to use a dataset as large as possible by combining multiple datasets in the training. However, it is problematic and troublesome to naively combine different datasets due to two major issues. First, the same person can possibly appear in different datasets, leading to an identity overlapping issue between different datasets. Naively treating the same person as different classes in different datasets during training will affect back-propagation and generate non-representative embeddings. On the other hand, manually cleaning labels may take formidable human efforts, especially when there are millions of images and thousands of identities. Second, different datasets are collected in different situations and thus will lead to different domain distributions. Naively combining datasets will make it difficult to learn domain invariant embeddings across different datasets. In this paper, we propose DAIL: Dataset-Aware and Invariant Learning to resolve the above-mentioned issues. To solve the first issue of identity overlapping, we propose a dataset-aware loss for multi-dataset training by reducing the penalty when the same person appears in multiple datasets. This can be readily achieved with a modified softmax loss with a dataset-aware term. To solve the second issue, domain adaptation with gradient reversal layers is employed for dataset invariant learning. The proposed approach not only achieves state-of-the-art results on several commonly used face recognition validation sets, including LFW, CFP-FP, and AgeDB-30, but also shows great benefit for practical use.