Metraipolis › archive › dc_6fc442d2c50d

ArmorOCR: Grounded Adversarial Visual Perception via Observation-Transferred Self-Distillation — arXiv:2608.20122

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20122
License (as archived)
CC0-1.0
Archived
2026-10-18T12:04:47.158Z
SHA-256 of the archived text
85de2dea07a5708e70cd7f535ec1504a6a7a47cae442e428a8f269c8e877d738
Stable URL of this page
https://metraipolis.com/documento/dc_6fc442d2c50d

How to cite

ArmorOCR: Grounded Adversarial Visual Perception via Observation-Transferred Self-Distillation — arXiv:2608.20122 — arXiv (en), https://arxiv.org/abs/2608.20122 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6fc442d2c50d (Metraipolis archive dc_6fc442d2c50d, sha256 85de2dea07a5708e70cd7f535ec1504a6a7a47cae442e428a8f269c8e877d738)
BibTeX
@misc{dc6fc442d2c50d,
  title = {ArmorOCR: Grounded Adversarial Visual Perception via Observation-Transferred Self-Distillation — arXiv:2608.20122},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20122},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6fc442d2c50d; sha256 85de2dea07a5708e70cd7f535ec1504a6a7a47cae442e428a8f269c8e877d738},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20122. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large multimodal models (LMMs) have demonstrated strong OCR recognition capabilities, yet remain vulnerable to adversarial visual text that is readable to humans but challenging for models to localize and recognize. Existing OCR benchmarks mainly focus on natural or document-style text, while adversarial OCR evaluations remain limited in scale, task coverage, or region-aware evaluation. In this paper, we formulate adversarial OCR as a \textbf{grounded OCR perception} task and introduce \textbf{AdvSpot}, the first benchmark for grounded adversarial OCR evaluation. AdvSpot comprises 390 images with region-level annotations, spanning 5 primary categories and 13 fine-grained adversarial OCR types. To address this challenge, we propose \textbf{ArmorOCR}, a two-stage training framework for robust adversarial OCR perception. ArmorOCR first acquires missing adversarial OCR perception from privileged transformed observations through On-Policy Self-Distillation (OPSD), and then refines grounded OCR perception through Group Relative Policy Optimization (GRPO) with task-conditioned rewards for localization, recognition, full spotting, and visual question answering (VQA). Experiments on our AdvSpot, other adversarial OCR benchmarks, and general OCR benchmarks demonstrate that ArmorOCR consistently improves adversarial OCR perception while preserving competitive general OCR capability.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.20122 — 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 2026-10-18T12:01:57.737Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).