# Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC

arXiv: https://arxiv.org/abs/2203.15565 · HTML: https://mlsanity.com/paper/2203.15565/

## Key facts

- Cited by 74 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 50 references that are in the map.
- First posted on arXiv 28 Mar 2022.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [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)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Data Uncertainty Learning in Face Recognition](https://mlsanity.com/paper/2003.11339/) (2020)
- [A Light CNN for Deep Face Representation with Noisy Labels](https://mlsanity.com/paper/1511.02683/) (2015)
- [AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations](https://mlsanity.com/paper/1905.00292/) (2019)
- [Towards Universal Representation Learning for Deep Face Recognition](https://mlsanity.com/paper/2002.11841/) (2020)
- [The Devil of Face Recognition is in the Noise](https://mlsanity.com/paper/1807.11649/) (2018)
- [Mis-classified Vector Guided Softmax Loss for Face Recognition](https://mlsanity.com/paper/1912.00833/) (2019)
- [Masked Face Recognition Challenge: The InsightFace Track Report](https://mlsanity.com/paper/2108.08191/) (2021)
- [Consistent Instance False Positive Improves Fairness in Face Recognition](https://mlsanity.com/paper/2106.05519/) (2021)
- [GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognition](https://mlsanity.com/paper/2005.10497/) (2020)
- [Domain Balancing: Face Recognition on Long-Tailed Domains](https://mlsanity.com/paper/2003.13791/) (2020)
- [BroadFace: Looking at Tens of Thousands of People at Once for Face Recognition](https://mlsanity.com/paper/2008.06674/) (2020)
- [Noise-Tolerant Paradigm for Training Face Recognition CNNs](https://mlsanity.com/paper/1903.10357/) (2019)
- [Semi-Siamese Training for Shallow Face Learning](https://mlsanity.com/paper/2007.08398/) (2020)
- [Accelerated Training for Massive Classification via Dynamic Class Selection](https://mlsanity.com/paper/1801.01687/) (2018)
- [P2SGrad: Refined Gradients for Optimizing Deep Face Models](https://mlsanity.com/paper/1905.02479/) (2019)
- [Dynamic Class Queue for Large Scale Face Recognition In the Wild](https://mlsanity.com/paper/2105.11113/) (2021)
- [Softmax Dissection: Towards Understanding Intra- and Inter-class Objective for Embedding Learning](https://mlsanity.com/paper/1908.01281/) (2019)
- [Large-scale Bisample Learning on ID Versus Spot Face Recognition](https://mlsanity.com/paper/1806.03018/) (2018)

## Built on by (most cited first, 30 of 74)

- [DiffFace: Diffusion-based Face Swapping with Facial Guidance](https://mlsanity.com/paper/2212.13344/) (2022)
- [KeyPoint Relative Position Encoding for Face Recognition](https://mlsanity.com/paper/2403.14852/) (2024)
- [Unicom: Universal and Compact Representation Learning for Image Retrieval](https://mlsanity.com/paper/2304.05884/) (2023)
- [VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention](https://mlsanity.com/paper/2503.15138/) (2025)
- [EdgeFace: Efficient Face Recognition Model for Edge Devices](https://mlsanity.com/paper/2307.01838/) (2023)
- [Benchmarking Algorithmic Bias in Face Recognition: An Experimental Approach Using Synthetic Faces and Human Evaluation](https://mlsanity.com/paper/2308.05441/) (2023)
- [Multi-modal Facial Affective Analysis based on Masked Autoencoder](https://mlsanity.com/paper/2303.10849/) (2023)
- [TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Security](https://mlsanity.com/paper/2308.10133/) (2023)
- [CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination](https://mlsanity.com/paper/2408.09441/) (2024)
- [Leveraging TCN and Transformer for effective visual-audio fusion in continuous emotion recognition](https://mlsanity.com/paper/2303.08356/) (2023)
- [A Quality Aware Sample-to-Sample Comparison for Face Recognition](https://mlsanity.com/paper/2306.04000/) (2023)
- [Multi-label Cluster Discrimination for Visual Representation Learning](https://mlsanity.com/paper/2407.17331/) (2024)
- [ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation](https://mlsanity.com/paper/2503.17671/) (2025)
- [Personalized Face Inpainting with Diffusion Models by Parallel Visual Attention](https://mlsanity.com/paper/2312.03556/) (2023)
- [Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics](https://mlsanity.com/paper/2402.09225/) (2024)
- [LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition](https://mlsanity.com/paper/2403.08161/) (2024)
- [TopoFR: A Closer Look at Topology Alignment on Face Recognition](https://mlsanity.com/paper/2410.10587/) (2024)
- [Region-based Cluster Discrimination for Visual Representation Learning](https://mlsanity.com/paper/2507.20025/) (2025)
- [LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognition](https://mlsanity.com/paper/2501.13420/) (2025)
- [UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition](https://mlsanity.com/paper/2311.02523/) (2023)
- [HSEmotion Team at the 6th ABAW Competition: Facial Expressions, Valence-Arousal and Emotion Intensity Prediction](https://mlsanity.com/paper/2403.11590/) (2024)
- [VariFace: Fair and Diverse Synthetic Dataset Generation for Face Recognition](https://mlsanity.com/paper/2412.06235/) (2024)
- [HelloMeme: Integrating Spatial Knitting Attentions to Embed High-Level and Fidelity-Rich Conditions in Diffusion Models](https://mlsanity.com/paper/2410.22901/) (2024)
- [VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention](https://mlsanity.com/paper/2412.02259/) (2024)
- [Perspective Reconstruction of Human Faces by Joint Mesh and Landmark Regression](https://mlsanity.com/paper/2208.07142/) (2022)
- [A Brief Survey on Person Recognition at a Distance](https://mlsanity.com/paper/2212.08969/) (2022)
- [PATMAT: Person Aware Tuning of Mask-Aware Transformer for Face Inpainting](https://mlsanity.com/paper/2304.06107/) (2023)
- [Generalized Face Liveness Detection via De-fake Face Generator](https://mlsanity.com/paper/2401.09006/) (2024)
- [FROQ: Observing Face Recognition Models for Efficient Quality Assessment](https://mlsanity.com/paper/2509.17689/) (2025)
- [Hyperspherical Classification with Dynamic Label-to-Prototype Assignment](https://mlsanity.com/paper/2403.16937/) (2024)

## Abstract (arXiv)

Learning discriminative deep feature embeddings by using million-scale in-the-wild datasets and margin-based softmax loss is the current state-of-the-art approach for face recognition. However, the memory and computing cost of the Fully Connected (FC) layer linearly scales up to the number of identities in the training set. Besides, the large-scale training data inevitably suffers from inter-class conflict and long-tailed distribution. In this paper, we propose a sparsely updating variant of the FC layer, named Partial FC (PFC). In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss. All class centers are still maintained throughout the whole training process, but only a subset is selected and updated in each iteration. Therefore, the computing requirement, the probability of inter-class conflict, and the frequency of passive update on tail class centers, are dramatically reduced. Extensive experiments across different training data and backbones (e.g. CNN and ViT) confirm the effectiveness, robustness and efficiency of the proposed PFC. The source code is available at https://github.com/deepinsight/insightface/tree/master/recognition.