Benchmarking CLIP for Zero-Shot Face and Periocular Gender Estimation

Fernando Alonso-Fernandez, Kevin Hernandez-Diaz, Jose Maria Buades, Josef Bigun
10/5/2026
cs.CV

No confident code implementation found for this paper.

Abstract

We investigate CLIP for zero-shot gender estimation from full-face and periocular images. Three CLIP backbones are evaluated on 11,299 frontal images from Adience using image-text similarity with male/female prompts, achieving 95.54% full-face accuracy without task-specific training. For periocular, zero-shot predictions are strongly biased towards males, primarily due to a misaligned decision boundary. Threshold alignment substantially reduces this bias, reaching 85.29% accuracy. Linear SVMs trained on CLIP features provide only marginal gains, with a best periocular accuracy of 86.17%, approximately 2.8% above previous Adience results in the literature. Nevertheless, the gap with full-face performance confirms the greater difficulty of periocular gender estimation

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Vision-Language Models Performing Zero-Shot Tasks Exhibit Gender-based Disparities

82% match2023

On the "Illusion" of Gender Bias in Face Recognition: Explaining the Fairness Issue Through Non-demographic Attributes

82% match2025

Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?

81% match2025

Vision-Language Models display a strong gender bias

81% match2025

Exploring the Feasibility of Deep Learning Techniques for Accurate Gender Classification from Eye Images

80% match2025

VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution

80% match1 repo132026

Cite this paper

@article{alonsofernandez2026benchmarking,
  title  = {Benchmarking CLIP for Zero-Shot Face and Periocular Gender Estimation},
  author = {Fernando Alonso-Fernandez and Kevin Hernandez-Diaz and Jose Maria Buades and Josef Bigun},
  year   = {2026},
  eprint = {2610.06102},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2610.06102v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2610.06102.svg)](https://codeofpaper.com/paper/2610.06102)

Discussion