Metraipolis › archive › dc_f43c237f989e
What Input Resolution Is Required for Bird Species Identification, and What Is Its Latency Cost on an Edge Device? A Study of 14 Input Resolutions and Six Architectures… — arXiv:2609.14247
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14247
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:15:31.112Z
- SHA-256 of the archived text
0170dab622f65b86ebc84df97f5bae169a9fd693ea2523aaa70826ea37cc3b9b- Stable URL of this page
https://metraipolis.com/documento/dc_f43c237f989e
How to cite
What Input Resolution Is Required for Bird Species Identification, and What Is Its Latency Cost on an Edge Device? A Study of 14 Input Resolutions and Six Architectures… — arXiv:2609.14247 — arXiv (en), https://arxiv.org/abs/2609.14247 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f43c237f989e (Metraipolis archive dc_f43c237f989e, sha256 0170dab622f65b86ebc84df97f5bae169a9fd693ea2523aaa70826ea37cc3b9b)
BibTeX
@misc{dcf43c237f989e,
title = {What Input Resolution Is Required for Bird Species Identification, and What Is Its Latency Cost on an Edge Device? A Study of 14 Input Resolutions and Six Architectures… — arXiv:2609.14247},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14247},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f43c237f989e; sha256 0170dab622f65b86ebc84df97f5bae169a9fd693ea2523aaa70826ea37cc3b9b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14247. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Bird-strike mitigation at wind farms requires identifying distant birds that span only tens of pixels, so the classifier's input resolution N is a design variable, not a fixed specification. We study it with a factorial design over 14 side lengths N (16 to 224), six architectures, two training and evaluation regimes and 30 random seeds -- 2,520 checkpoints and 5,040 evaluations -- plus latency measured on an NVIDIA Jetson Orin Nano. Four results. (1) The selected N depends on the target: 0.90 is met on validation by ResNet50 at N=112 in an estimated 1.85 ms (0.8980 on test) and 0.95 by DINOv2-L at N=144 in 12.70 ms; changing the model buys more accuracy than raising N (+5.93 versus +2.33 points at N=112). (2) The benefit of lowering N depends on the assumed preprocessing path: N=224 -> 80 saves 13.5% when each individual is decoded from its own file but 46.2% when the detector decodes the 4K frame once; the Pareto set grows from 20 to 23 configurations. (3) Accuracy must be measured on the deployed engine: half precision costs ViT-S/16 alone 4 to 7 points at N>=96 while the CNNs stay within 0.1 points, and with selection held at validation the choice differs at 26 of 176 targets. A broken FP16 engine can run faster than a correct one, undetectable from latency; admitting 14 ViT-S/16 FP32 configurations moves the recommendation over the 0.931-0.938 band and under the 10 ms budget. (4) ViT-L-scale models fit this device, but activations exceed the FP16 range; splitting the graph at transformer-block boundaries confines FP32 to the affected segments, making the deployed DINOv2-L chain 1.85x faster than the single-engine build. We also quantify how the regime-difference sign stabilises with seed count; a sensitivity split removing some forms of group sharing preserves all 14 non-trivial signs at the selection boundary. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Image and Video Processing (eess.IV). Pagina del lavoro: https://arxiv.org/abs/2609.14247 — 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 2026-10-15T23:54:14.896Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).