Robustness and Localization Analysis of Adaptive Multiscale Attention for Balsa Wood Defect Detection
Identification
- Clé publique
- radar:r-8ce3eec8096331cb0e1dd63da3b377c8
- Auteurs
- Cristian G. Zambrano-Vega · Joel Cedeño-Muñoz · Washington Chiriboga Casanova · Byron Oviedo · Efraín Díaz-Macías · Edgar Atilio Suárez Bardelline
- Année déclarée
- 2026
- Langue déclarée
- en
- Type source
- article
- Première détection
- 2026-11-14T01:59:49.873703+00:00
- Dernière observation des métadonnées
- 2026-11-14T01:59:49.873703+00:00
- Dernière vérification HTTP
- Non effectuée
Institutions déclarées par la source
Universidad Técnica Estatal de Quevedo
Pays d’affiliation déclarés
EC
Résumé documentaire — langue originale
Balsa wood defects can resemble natural grain, making successful detection insufficient to establish precise localization or robustness to acquisition changes. This study investigates these limitations using the previously published YOLOv11–BiFPN–DAAF framework as a reference for analyzing adaptive multiscale attention. On a 508-image industrial dataset, five training seeds support selected-IoU evaluation, geometric box-error analysis, stratification by defect size, contrast, and elongation, and controlled comparisons of within-scale attention and mixing operators. Robustness is assessed under 15 brightness, contrast, noise, blur, and compression conditions and an external production campaign. Relative to YOLOv11, the complete framework increases internal-test AP from 0.865 to 0.892 at IoU 0.50, from 0.385 to 0.442 at IoU 0.75, and from 0.082 to 0.125 at IoU 0.90, while reducing mean geometric errors among matched detections. It improves mAP@0.5:0.95 by 0.035 (paired-seed 95% CI: 0.03061–0.03939) and exhibits smaller mean degradation under every tested perturbation, while external mAP@0.5:0.95 decreases from the internal value of 0.384 to 0.358. In the within-scale ablation, learned gating exceeds fixed mixing by 0.003 in mean mAP@0.5:0.95 (0.384 versus 0.381), with additional trainable capacity. Composite spatial-attention maps yield a concentration ratio of 4.8±0.7, indicating higher mean weights inside annotation boxes without establishing a causal suppression mechanism. Paired statistical analyses distinguish training-seed variability from test-panel uncertainty. The findings identify localization gains, acquisition sensitivities, and the observed contribution of adaptive refinement within the established architecture. They support further evaluation of difficult defects and independent production domains rather than unrestricted generalization claims.
Identifiants
- OPENALEX
- https://openalex.org/W7223252258
- DOI
- 10.3390/signals7060105
Repères documentaires
- Famille documentaire
- article
- Types déclarés par les sources
- article
- Éditeurs
- Multidisciplinary Digital Publishing Institute
Les mentions d’entités ne constituent pas une preuve de reconnaissance juridique. La juridiction étudiée est distincte du pays d’affiliation des auteurs.
Sources
OpenAlex · Document 1
Citer cette référence
Cristian G. Zambrano-Vega; Joel Cedeño-Muñoz; Washington Chiriboga Casanova; Byron Oviedo; Efraín Díaz-Macías; Edgar Atilio Suárez Bardelline. Robustness and Localization Analysis of Adaptive Multiscale Attention for Balsa Wood Defect Detection. 2026. https://doi.org/10.3390/signals7060105
JSON · CSL-JSON · BibTeX · RIS · CSV · JSON-LD ·
APA, Chicago, ISO 690 : formats bibliographiques fondés sur les champs disponibles. OSCOLA / Bluebook : données structurées uniquement ; aucune conformité juridique complète n’est revendiquée sans vérification des éléments nécessaires.
- APA
- Cristian G. Zambrano-Vega; Joel Cedeño-Muñoz; Washington Chiriboga Casanova; Byron Oviedo; Efraín Díaz-Macías; Edgar Atilio Suárez Bardelline. (2026). Robustness and Localization Analysis of Adaptive Multiscale Attention for Balsa Wood Defect Detection. https://doi.org/10.3390/signals7060105
- Chicago
- Cristian G. Zambrano-Vega; Joel Cedeño-Muñoz; Washington Chiriboga Casanova; Byron Oviedo; Efraín Díaz-Macías; Edgar Atilio Suárez Bardelline. Robustness and Localization Analysis of Adaptive Multiscale Attention for Balsa Wood Defect Detection. 2026. https://doi.org/10.3390/signals7060105
- ISO 690
- Cristian G. Zambrano-Vega; Joel Cedeño-Muñoz; Washington Chiriboga Casanova; Byron Oviedo; Efraín Díaz-Macías; Edgar Atilio Suárez Bardelline. Robustness and Localization Analysis of Adaptive Multiscale Attention for Balsa Wood Defect Detection. 2026. https://doi.org/10.3390/signals7060105
Warning: Undefined array key "last_link_verified" in /home/clients/e27d81e12f04d2bfd747aa264540ac56/sites/_UDTR_APP/legal_library_reference.php on line 31
UDTR — Bibliothèque juridique mondiale des droits de la Nature. Robustness and Localization Analysis of Adaptive Multiscale Attention for Balsa Wood Defect Detection. Notice documentaire: https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-8ce3eec8096331cb0e1dd63da3b377c8/ · Dernière vérification HTTP : non effectuée
Données de cette version figée
Dossiers et relations documentaires
Rôles des sources
Source bibliographique / publication d’origine · https://doi.org/10.3390/signals7060105
Un lien vers une autorité ne prouve pas à lui seul une affirmation juridique. Les résumés et les textes intégraux restent soumis aux conditions de leur source.
Statut documentaire
Pertinence à examiner
Bibliothèque
Cette identité n’est pas encore intégrée à la Bibliothèque juridique.