SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Data

• URL: http://arxiv.org/abs/2308.14852v1
• Date: Mon, 28 Aug 2023 19:15:27 GMT
• Title: SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Data
• Authors: Hatef Otroshi Shahreza, Anjith George, S\'ebastien Marcel
• Abstract summary: State-of-the-art face recognition networks are often computationally expensive and cannot be used for mobile applications. We propose a new framework to train lightweight face recognition models by distilling the knowledge of a pretrained teacher face recognition model using synthetic data. We use synthetic face images without identity labels, mitigating the problems in the intra-class variation generation of synthetic datasets.
• Score: 8.026313049094146
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: State-of-the-art face recognition networks are often computationally expensive and cannot be used for mobile applications. Training lightweight face recognition models also requires large identity-labeled datasets. Meanwhile, there are privacy and ethical concerns with collecting and using large face recognition datasets. While generating synthetic datasets for training face recognition models is an alternative option, it is challenging to generate synthetic data with sufficient intra-class variations. In addition, there is still a considerable gap between the performance of models trained on real and synthetic data. In this paper, we propose a new framework (named SynthDistill) to train lightweight face recognition models by distilling the knowledge of a pretrained teacher face recognition model using synthetic data. We use a pretrained face generator network to generate synthetic face images and use the synthesized images to learn a lightweight student network. We use synthetic face images without identity labels, mitigating the problems in the intra-class variation generation of synthetic datasets. Instead, we propose a novel dynamic sampling strategy from the intermediate latent space of the face generator network to include new variations of the challenging images while further exploring new face images in the training batch. The results on five different face recognition datasets demonstrate the superiority of our lightweight model compared to models trained on previous synthetic datasets, achieving a verification accuracy of 99.52% on the LFW dataset with a lightweight network. The results also show that our proposed framework significantly reduces the gap between training with real and synthetic data. The source code for replicating the experiments is publicly released.

Related papers

• Unveiling Synthetic Faces: How Synthetic Datasets Can Expose Real Identities [22.8742248559748]
  We show that in 6 state-of-the-art synthetic face recognition datasets, several samples from the original real dataset are leaked. This paper is the first work which shows the leakage from training data of generator models into the generated synthetic face recognition datasets.
  arXiv  Detail & Related papers  (2024-10-31T15:17:14Z)
• Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data [104.45155847778584]
  This paper presents an overview of the 2nd edition of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) FRCSyn aims to investigate the use of synthetic data in face recognition to address current technological limitations.
  arXiv  Detail & Related papers  (2024-04-16T08:15:10Z)
• SDFR: Synthetic Data for Face Recognition Competition [51.9134406629509]
  Large-scale face recognition datasets are collected by crawling the Internet and without individuals' consent, raising legal, ethical, and privacy concerns. Recently several works proposed generating synthetic face recognition datasets to mitigate concerns in web-crawled face recognition datasets. This paper presents the summary of the Synthetic Data for Face Recognition (SDFR) Competition held in conjunction with the 18th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2024) The SDFR competition was split into two tasks, allowing participants to train face recognition systems using new synthetic datasets and/or existing ones.
  arXiv  Detail & Related papers  (2024-04-06T10:30:31Z)
• If It's Not Enough, Make It So: Reducing Authentic Data Demand in Face Recognition through Synthetic Faces [16.977459035497162]
  Large face datasets are primarily sourced from web-based images, lacking explicit user consent. In this paper, we examine whether and how synthetic face data can be used to train effective face recognition models.
  arXiv  Detail & Related papers  (2024-04-04T15:45:25Z)
• Is Synthetic Image Useful for Transfer Learning? An Investigation into Data Generation, Volume, and Utilization [62.157627519792946]
  We introduce a novel framework called bridged transfer, which initially employs synthetic images for fine-tuning a pre-trained model to improve its transferability. We propose dataset style inversion strategy to improve the stylistic alignment between synthetic and real images. Our proposed methods are evaluated across 10 different datasets and 5 distinct models, demonstrating consistent improvements.
  arXiv  Detail & Related papers  (2024-03-28T22:25:05Z)
• Is synthetic data from generative models ready for image recognition? [69.42645602062024]
  We study whether and how synthetic images generated from state-of-the-art text-to-image generation models can be used for image recognition tasks. We showcase the powerfulness and shortcomings of synthetic data from existing generative models, and propose strategies for better applying synthetic data for recognition tasks.
  arXiv  Detail & Related papers  (2022-10-14T06:54:24Z)
• SynFace: Face Recognition with Synthetic Data [83.15838126703719]
  We devise the SynFace with identity mixup (IM) and domain mixup (DM) to mitigate the performance gap. We also perform a systematically empirical analysis on synthetic face images to provide some insights on how to effectively utilize synthetic data for face recognition.
  arXiv  Detail & Related papers  (2021-08-18T03:41:54Z)
• Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognition [61.87842307164351]
  We first propose an Identity-Aware CycleGAN (IACycleGAN) model that applies a new perceptual loss to supervise the image generation network. It improves CycleGAN on photo-sketch synthesis by paying more attention to the synthesis of key facial regions, such as eyes and nose. We develop a mutual optimization procedure between the synthesis model and the recognition model, which iteratively synthesizes better images by IACycleGAN.
  arXiv  Detail & Related papers  (2021-03-30T01:30:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.