Identity-Preserving Aging of Face Images via Latent Diffusion Models
- URL: http://arxiv.org/abs/2307.08585v1
- Date: Mon, 17 Jul 2023 15:57:52 GMT
- Title: Identity-Preserving Aging of Face Images via Latent Diffusion Models
- Authors: Sudipta Banerjee, Govind Mittal, Ameya Joshi, Chinmay Hegde, Nasir
Memon
- Abstract summary: We propose, train, and validate the use of latent text-to-image diffusion models for synthetically aging and de-aging face images.
Our models succeed with few-shot training, and have the added benefit of being controllable via intuitive textual prompting.
- Score: 22.2699253042219
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The performance of automated face recognition systems is inevitably impacted
by the facial aging process. However, high quality datasets of individuals
collected over several years are typically small in scale. In this work, we
propose, train, and validate the use of latent text-to-image diffusion models
for synthetically aging and de-aging face images. Our models succeed with
few-shot training, and have the added benefit of being controllable via
intuitive textual prompting. We observe high degrees of visual realism in the
generated images while maintaining biometric fidelity measured by commonly used
metrics. We evaluate our method on two benchmark datasets (CelebA and AgeDB)
and observe significant reduction (~44%) in the False Non-Match Rate compared
to existing state-of the-art baselines.
Related papers
- 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) - Active Generation for Image Classification [50.18107721267218]
We propose to address the efficiency of image generation by focusing on the specific needs and characteristics of the model.
With a central tenet of active learning, our method, named ActGen, takes a training-aware approach to image generation.
arXiv Detail & Related papers (2024-03-11T08:45:31Z) - Effective Adapter for Face Recognition in the Wild [72.75516495170199]
We tackle the challenge of face recognition in the wild, where images often suffer from low quality and real-world distortions.
Traditional approaches-either training models directly on degraded images or their enhanced counterparts using face restoration techniques-have proven ineffective.
We propose an effective adapter for augmenting existing face recognition models trained on high-quality facial datasets.
arXiv Detail & Related papers (2023-12-04T08:55:46Z) - Limitations of Face Image Generation [12.11955119100926]
We study the efficacy and shortcomings of generative models in the context of face generation.
We identify several limitations of face image generation that include faithfulness to the text prompt, demographic disparities, and distributional shifts.
We present an analytical model that provides insights into how training data selection contributes to the performance of generative models.
arXiv Detail & Related papers (2023-09-13T19:33:26Z) - Will your Doorbell Camera still recognize you as you grow old [1.6536018920603175]
This work explores the effect of age and aging on the performance of facial authentication methods.
A photo-realistic age transformation method has been employed to augment a set of high-quality facial images with various age effects.
The effect of these synthetic aging data on the high-performance deep-learning-based face recognition model is quantified.
arXiv Detail & Related papers (2023-08-08T12:43:26Z) - MiVOLO: Multi-input Transformer for Age and Gender Estimation [0.0]
We present MiVOLO, a straightforward approach for age and gender estimation using the latest vision transformer.
Our method integrates both tasks into a unified dual input/output model.
We compare our model's age recognition performance with human-level accuracy and demonstrate that it significantly outperforms humans across a majority of age ranges.
arXiv Detail & Related papers (2023-07-10T14:58:10Z) - 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) - FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in
the Wild [50.8865921538953]
We propose a method to explicitly incorporate facial semantics into age estimation.
We design a face parsing-based network to learn semantic information at different scales.
We show that our method consistently outperforms all existing age estimation methods.
arXiv Detail & Related papers (2021-06-21T14:31:32Z) - The FaceChannel: A Fast & Furious Deep Neural Network for Facial
Expression Recognition [71.24825724518847]
Current state-of-the-art models for automatic Facial Expression Recognition (FER) are based on very deep neural networks that are effective but rather expensive to train.
We formalize the FaceChannel, a light-weight neural network that has much fewer parameters than common deep neural networks.
We demonstrate how our model achieves a comparable, if not better, performance to the current state-of-the-art in FER.
arXiv Detail & Related papers (2020-09-15T09:25:37Z) - Joint Deep Learning of Facial Expression Synthesis and Recognition [97.19528464266824]
We propose a novel joint deep learning of facial expression synthesis and recognition method for effective FER.
The proposed method involves a two-stage learning procedure. Firstly, a facial expression synthesis generative adversarial network (FESGAN) is pre-trained to generate facial images with different facial expressions.
In order to alleviate the problem of data bias between the real images and the synthetic images, we propose an intra-class loss with a novel real data-guided back-propagation (RDBP) algorithm.
arXiv Detail & Related papers (2020-02-06T10:56:00Z)
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.