ADCF-YOLO: Aligning, Stabilizing and Decoupling Multi-Scale Features for Fine-Grained Refueling Interface Detection
Machines · 18.11.2026 · 14 (11) · 1371
DOI: 10.3390/machines14111371 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machines, online erschienen am 18.11.2026. Verfasst von Shengyou Zhou und 6 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Research Program of Chongqing Municipal Education Commission, Chongqing Municipal Graduate Research Innovation, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
High-precision detection of refueling interfaces on special equipment is a prerequisite for robots to carry out intelligent refueling operations. However, the lack of datasets in this field, together with the presence of multiple connectors that are visually similar but functionally different in real refueling environments, makes existing methods difficult to transfer effectively. To this end, we constructed the Refueling Interface Dataset, which contains 10 categories, 946 images and 7659 bounding boxes, with an average class-wise cosine similarity of 0.956, forming a fine-grained benchmark of visually similar, weakly textured connectors. Based on YOLO26, we propose ADCF-YOLO, which improves cross-scale feature fusion in the neck and the training supervision. Adaptive Deformable Cross-scale Fusion compensates for the spatial misalignment introduced by upsampling and convolution through a neighborhood convex combination and fuses the two paths with a zero-initialized residual gate. Sub-pixel Phase-Stable Detection (SPSD) exploits the known and invertible sub-pixel shift to map shifted-view predictions back to the original coordinate system, converting an invariance requirement into dense, unambiguous pixel-wise supervision. Counterfactual Context Decoupling (CCD) applies two oppositely directed constraints—annulus replacement and target erasure—to suppress reliance on background features. On the refueling interface dataset, ADCF-YOLO raises mAP@0.5 from 0.934 to 0.959 and mAP@0.5:0.95 from 0.482 to 0.526 over YOLO26n, the highest of the six YOLO-family detectors at this scale, and yields positive gains on two public datasets. The two Transformer-based reference detectors that score higher do so by 0.002–0.007 on the two mAP metrics, at 7.2–16.4 times the GFLOPs and 11.5–11.9 times the parameters. The engineering value lies in deployment: SPSD and CCD act only during training and leave the inference graph and its cost unchanged, so the accuracy gain carries no additional inference cost.
Förderung
- Science and Technology Research Program of Chongqing Municipal Education Commission
- Chongqing Municipal Graduate Research Innovation
- China Postdoctoral Science Foundation
Zitieren
APA
Zhou, S., Cui, W., Chen, S., Wu, Z., Fang, G., Hua, W., & Chen, Y. (2026). ADCF-YOLO: Aligning, Stabilizing and Decoupling Multi-Scale Features for Fine-Grained Refueling Interface Detection. Machines, 14(11), 1371. https://doi.org/10.3390/machines14111371
Vancouver
Zhou S, Cui W, Chen S, Wu Z, Fang G, Hua W, et al. ADCF-YOLO: Aligning, Stabilizing and Decoupling Multi-Scale Features for Fine-Grained Refueling Interface Detection. Machines. 2026;14(11):1371. doi:10.3390/machines14111371
BibTeX
@article{Zhou2026,
author = {Zhou, Shengyou and Cui, Wen and Chen, Shiming and Wu, Zhaojie and Fang, Gang and Hua, Weixing and Chen, Yan},
title = {ADCF-YOLO: Aligning, Stabilizing and Decoupling Multi-Scale Features for Fine-Grained Refueling Interface Detection},
journal = {Machines},
year = {2026},
volume = {14},
number = {11},
pages = {1371},
doi = {10.3390/machines14111371}
}
EUVIMED