Can Text-to-Image Generative Models Accurately Depict Age? A Comparative Study on Synthetic Portrait Generation and Age Estimation

• URL: http://arxiv.org/abs/2502.03420v1
• Date: Wed, 05 Feb 2025 18:08:33 GMT
• Title: Can Text-to-Image Generative Models Accurately Depict Age? A Comparative Study on Synthetic Portrait Generation and Age Estimation
• Authors: Alexey A. Novikov, Miroslav Vranka, François David, Artem Voronin,
• Abstract summary: Text-to-image generative models have shown remarkable progress in producing diverse and photorealistic outputs. We present a comprehensive analysis of their effectiveness in creating synthetic portraits that accurately represent various demographic attributes. Our evaluation employs prompts specifying detailed profiles covering a broad spectrum of 212 nationalities, 30 distinct ages from 10 to 78, and balanced gender representation.
• Score: 0.33998740964877455
• License:
• Abstract: Text-to-image generative models have shown remarkable progress in producing diverse and photorealistic outputs. In this paper, we present a comprehensive analysis of their effectiveness in creating synthetic portraits that accurately represent various demographic attributes, with a special focus on age, nationality, and gender. Our evaluation employs prompts specifying detailed profiles (e.g., Photorealistic selfie photo of a 32-year-old Canadian male), covering a broad spectrum of 212 nationalities, 30 distinct ages from 10 to 78, and balanced gender representation. We compare the generated images against ground truth age estimates from two established age estimation models to assess how faithfully age is depicted. Our findings reveal that although text-to-image models can consistently generate faces reflecting different identities, the accuracy with which they capture specific ages and do so across diverse demographic backgrounds remains highly variable. These results suggest that current synthetic data may be insufficiently reliable for high-stakes age-related tasks requiring robust precision, unless practitioners are prepared to invest in significant filtering and curation. Nevertheless, they may still be useful in less sensitive or exploratory applications, where absolute age precision is not critical.

Related papers

• Synthetic Face Ageing: Evaluation, Analysis and Facilitation of Age-Robust Facial Recognition Algorithms [1.0499611180329804]
  We explore the feasibility of utilizing synthetic ageing data to improve the robustness of face recognition models. We show that the recognition rate of the model trained on synthetic ageing images is 3.33% higher than the results of the baseline model when tested on images with an age gap of 40 years.
  arXiv  Detail & Related papers  (2024-06-10T14:27:36Z)
• New Job, New Gender? Measuring the Social Bias in Image Generation Models [85.26441602999014]
  Image generation models are susceptible to generating content that perpetuates social stereotypes and biases. We propose BiasPainter, a framework that can accurately, automatically and comprehensively trigger social bias in image generation models. BiasPainter can achieve 90.8% accuracy on automatic bias detection, which is significantly higher than the results reported in previous work.
  arXiv  Detail & Related papers  (2024-01-01T14:06:55Z)
• DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models [73.12069620086311]
  We investigate the visual reasoning capabilities and social biases of text-to-image models. First, we measure three visual reasoning skills: object recognition, object counting, and spatial relation understanding. Second, we assess the gender and skin tone biases by measuring the gender/skin tone distribution of generated images.
  arXiv  Detail & Related papers  (2022-02-08T18:36:52Z)
• Are Commercial Face Detection Models as Biased as Academic Models? [64.71318433419636]
  We compare academic and commercial face detection systems, specifically examining robustness to noise. We find that state-of-the-art academic face detection models exhibit demographic disparities in their noise robustness. We conclude that commercial models are always as biased or more biased than an academic model.
  arXiv  Detail & Related papers  (2022-01-25T02:21:42Z)
• Applying Artificial Intelligence for Age Estimation in Digital Forensic Investigations [0.8122270502556371]
  Investigators often need to determine the age of victims by looking at images and interpreting the sexual development stages and other human characteristics. This paper evaluates existing facial image datasets and proposes a new dataset tailored to the needs of similar digital forensic research contributions. The new dataset is tested on the Deep EXpectation (DEX) algorithm pre-trained on the IMDB-WIKI dataset.
  arXiv  Detail & Related papers  (2022-01-09T16:25:37Z)
• 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)
• Enhance Gender and Identity Preservation in Face Aging Simulation for Infants and Toddlers [10.447210000352847]
  We propose a new deep learning method inspired by the Conditional Adversarial Autoencoder (CAAE, 2017) model. We trained our model using the publicly available UTKFace dataset and evaluated our model by simulating up to 100 years of aging on 1,156 male and 1,207 female infant and toddler face photos.
  arXiv  Detail & Related papers  (2020-11-15T01:40:36Z)
• Age Gap Reducer-GAN for Recognizing Age-Separated Faces [72.26969872180841]
  We propose a novel algorithm for matching faces with temporal variations caused due to age progression. The proposed generative adversarial network algorithm is a unified framework that combines facial age estimation and age-separated face verification.
  arXiv  Detail & Related papers  (2020-11-11T16:43:32Z)
• Age and Gender Prediction From Face Images Using Attentional Convolutional Network [6.3344832182228]
  We propose a deep learning framework, based on the ensemble of attentional and residual convolutional networks, to predict gender and age group of facial images with high accuracy rate. Our model is trained on a popular face age and gender dataset, and achieved promising results.
  arXiv  Detail & Related papers  (2020-10-08T06:33:55Z)
• Investigating Bias in Deep Face Analysis: The KANFace Dataset and Empirical Study [67.3961439193994]
  We introduce the most comprehensive, large-scale dataset of facial images and videos to date. The data are manually annotated in terms of identity, exact age, gender and kinship. A method to debias network embeddings is introduced and tested on the proposed benchmarks.
  arXiv  Detail & Related papers  (2020-05-15T00:14:39Z)
• An Overview of Two Age Synthesis and Estimation Techniques [6.114546762705721]
  Age estimation is a technique for predicting human ages from digital facial images. Age synthesis is defined to render a facial image with aesthetically rejuvenating and natural aging effects on the person's face.
  arXiv  Detail & Related papers  (2020-01-26T06:07:49Z)

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.