Metraipolis › archive › dc_95640e5ce73a
Frozen High-Resolution Inference for Cross-City Object Detection: An AI City Challenge 2026 Study — arXiv:2608.03136
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03136
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:58:15.818Z
- SHA-256 of the archived text
fde6056964ea55100375675dec50e80fb8de531eb904b0926016b6eddbbcd8d5- Stable URL of this page
https://metraipolis.com/documento/dc_95640e5ce73a
How to cite
Frozen High-Resolution Inference for Cross-City Object Detection: An AI City Challenge 2026 Study — arXiv:2608.03136 — arXiv (en), https://arxiv.org/abs/2608.03136 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_95640e5ce73a (Metraipolis archive dc_95640e5ce73a, sha256 fde6056964ea55100375675dec50e80fb8de531eb904b0926016b6eddbbcd8d5)
BibTeX
@misc{dc95640e5ce73a,
title = {Frozen High-Resolution Inference for Cross-City Object Detection: An AI City Challenge 2026 Study — arXiv:2608.03136},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03136},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_95640e5ce73a; sha256 fde6056964ea55100375675dec50e80fb8de531eb904b0926016b6eddbbcd8d5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03136. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Cross-city object detection requires a detector trained in one city to generalize to an unlabeled target city. In AI City Challenge 2026 Track 6, we analyze archived configurations of a single RF-DETR-Large detector inside an air-gapped Training-as-a-Service platform whose server returns only an aggregate COCO-style AP over a hidden mixture of source- and target-city images. Frozen 1120 x 1120 inference of a checkpoint trained at 704 x 704 achieved the highest aggregate AP among the evaluated configurations (0.3272 -> 0.3654, +0.0382) without any parameter update, with the largest relative gain on small objects and the largest absolute gain on medium objects, at 2.53x the input pixels. A warm-start 1120px fine-tuning recipe reached 0.3470 while its in-domain validation AP rose (0.767 -> 0.789), a caution that in-domain validation is an unreliable model-selection signal under aggregate-only cross-city feedback. Because that run's evaluation used a higher confidence threshold than the inference-only runs (0.05 vs. 0.01), we treat its score as a descriptive archived outcome rather than a controlled verdict on fine-tuning. Gray-world normalization did not meaningfully change the frozen-1120 result, and a rectangular run was found by audit to have used an unintended portrait orientation. We release verbatim platform commands, configuration snapshots, and an explicit evidence boundary for every claim. Each configuration was submitted once and the best was selected on the hidden server, so these are exploratory, audited findings about the aggregate mixture; they do not establish target-city-specific improvement. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.03136 — 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 2026-10-31T12:45:33.225Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).