Metraipolis › archive › dc_bf62df7ad539

Procedural Adversarial Learning — arXiv:2611.06890

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06890
License (as archived)
CC0-1.0
Archived
2026-11-05T18:30:15.169Z
SHA-256 of the archived text
4f66842891f3b5a0feea6c1754647f612ae95a174e5e580aa649213839f6daa4
Stable URL of this page
https://metraipolis.com/documento/dc_bf62df7ad539

How to cite

Procedural Adversarial Learning — arXiv:2611.06890 — arXiv (en), https://arxiv.org/abs/2611.06890 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf62df7ad539 (Metraipolis archive dc_bf62df7ad539, sha256 4f66842891f3b5a0feea6c1754647f612ae95a174e5e580aa649213839f6daa4)
BibTeX
@misc{dcbf62df7ad539,
  title = {Procedural Adversarial Learning — arXiv:2611.06890},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06890},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf62df7ad539; sha256 4f66842891f3b5a0feea6c1754647f612ae95a174e5e580aa649213839f6daa4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06890. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

For many computer vision tasks, neural networks can be trained to produce a low average error, yet they still fail on seemingly simple scenes. Reducing these failures requires first finding them, but they may not be in a fixed dataset. We study procedural adversarial learning (PAL), a framework of minimax training and adversarial evaluation which searches the input space of a procedural generator for difficult instances. The procedural generator is an interpretable program mapping a low-dimensional vector of control parameters (e.g. layout, lighting, pose) to a rendered image and its label. We introduce the Simple-PAT algorithm, which uses zeroth-order optimization in the procedural generator's parameter space to propose adversarial training samples that are generated on demand. We also create PAL-Dojo, a collection of efficient procedural generators for surface normal estimation, image segmentation, and human pose estimation. Against a cross-model black-box adversary with 50M aggregate queries, Simple-PAT reduces worst-case error by a geometric mean of 3.15x compared to standard training and 2.63x compared to the strongest robust training baseline. Code is available at this https URL .

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/2611.06890 — 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 2026-11-05T18:19:49.067Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).