Metraipolis › archive › dc_7495b08300fc
Adaptive Adversarial Augmentation for Controllable Face Synthesis — arXiv:2610.11356
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11356
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:30:29.940Z
- SHA-256 of the archived text
71650d388850d73a7ae1e426077e717eb1a64adeae6c711070dca3fa7fa0394e- Stable URL of this page
https://metraipolis.com/documento/dc_7495b08300fc
How to cite
Adaptive Adversarial Augmentation for Controllable Face Synthesis — arXiv:2610.11356 — arXiv (en), https://arxiv.org/abs/2610.11356 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7495b08300fc (Metraipolis archive dc_7495b08300fc, sha256 71650d388850d73a7ae1e426077e717eb1a64adeae6c711070dca3fa7fa0394e)
BibTeX
@misc{dc7495b08300fc,
title = {Adaptive Adversarial Augmentation for Controllable Face Synthesis — arXiv:2610.11356},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11356},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7495b08300fc; sha256 71650d388850d73a7ae1e426077e717eb1a64adeae6c711070dca3fa7fa0394e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11356. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Synthetic data provides a scalable alternative to real-world datasets for training face recognition models, particularly under challenging conditions such as low resolution, occlusion, and masks. Yet, most approaches lack diversity and fail to generalize effectively. We propose Ensemble Feedback Controllable Synthesis (EFCS), a guided framework that generates diverse and challenging samples while preserving visual realism. EFCS expands distributional variability, often reflected in higher FID and KID scores compared to single-feedback and random synthesis, while maintaining high precision. Recognition models trained on EFCS data consistently outperform baselines across multiple benchmarks, showing improved generalization to real-world scenarios. Furthermore, we introduce an analytically motivated formulation linking perturbation-induced difficulty, sample utility, and performance degradation, offering principled insights into balancing synthetic data complexity for optimal training. Together, these contributions establish EFCS as an effective and analytically grounded approach for bridging the gap between synthetic and real datasets. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.11356 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T05:55:07.312Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).