Metraipolis › archive › dc_0ce747716cbf
Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models — arXiv:2608.04190
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04190
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:12:32.355Z
- SHA-256 of the archived text
d613cda846effb1fa5c6ad3034bea4b4ce47ada553876f144b522ef1cfb87949- Stable URL of this page
https://metraipolis.com/documento/dc_0ce747716cbf
How to cite
Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models — arXiv:2608.04190 — arXiv (en), https://arxiv.org/abs/2608.04190 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0ce747716cbf (Metraipolis archive dc_0ce747716cbf, sha256 d613cda846effb1fa5c6ad3034bea4b4ce47ada553876f144b522ef1cfb87949)
BibTeX
@misc{dc0ce747716cbf,
title = {Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models — arXiv:2608.04190},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04190},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0ce747716cbf; sha256 d613cda846effb1fa5c6ad3034bea4b4ce47ada553876f144b522ef1cfb87949},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04190. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deploying pre-trained perception models in novel environments degrades their accuracy under distributional shift, and assembling them alone does not recover it: combiners such as majority voting trade recall for precision and are brittle to coordinated failures. Prior metacognitive methods learn logical rules that flag a model's errors, but rely on hand-authored domain-knowledge cues (object-size priors, segmentation masks) that do not transfer to genuinely novel scenes. We show that this metacognitive layer can be learned without any domain knowledge by exploiting vector-space geometry: per-model Label Vector Pools (LVP), built from each model's own training embeddings, yield error-detection rules from the geometry of detections relative to training-determined prototypes, reaching parity with domain-knowledge rules to within $0.002$ every F1 on test set. Because the approach remains neurosymbolic, these geometric rules share a single logical framework and can still be complemented by domain knowledge when available. We frame the fusion of multiple imperfect ViT-based detectors as a consistency-based abduction problem solved at test time by an exact Integer Program (IP) and a polynomial-time heuristic. On an aerial-imagery benchmark of 15 weather-shifted test sets and six ViT detectors, our domain-knowledge-free layer matches the strongest majority-vote variant on clean data (within $0.005$ F1) and, unlike every majority-vote baseline, retains its performance under a coordinated label-flipping attack: at a $90\%$ flip rate it averages $0.42$ F1 versus $0.35$ for MV-Plurality (a $22\%$ relative gain) and attains the highest F1 on \emph{every} test set once the flip rate exceeds $0.4$
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Logic in Computer Science (cs.LO).
Pagina del lavoro: https://arxiv.org/abs/2608.04190 — 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 2026-10-31T11:02:13.394Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).