{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:02:36Z","timestamp":1781881356305,"version":"3.54.5"},"reference-count":45,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T00:00:00Z","timestamp":1781827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the Natural Science Foundation of Xinjiang Uygur Autonomous Region","award":["2025D01C276"],"award-info":[{"award-number":["2025D01C276"]}]},{"name":"the Natural Science Foundation of Xinjiang Uygur Autonomous Region","award":["2025D14015"],"award-info":[{"award-number":["2025D14015"]}]},{"name":"the Xinjiang Tianchi Talent Program","award":["51052601848"],"award-info":[{"award-number":["51052601848"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Object detection in low-light scenes is difficult because weak illumination reduces local contrast, amplifies sensor noise, and makes small or occluded objects hard to localize. Existing enhancement-before-detection pipelines can improve visual brightness, but they are not always optimized for detection features, while transformer-style global reasoning is often too costly for lightweight detectors. To address this gap, we propose GE-Detection, a detector-side framework that integrates Global Sub-Sampled Attention (GSA), Efficient Multi-scale Attention (EMA), and dropout regularization into YOLO- and PicoDet-style architectures. GSA introduces lower-cost global context modeling through spatially reduced key-value tokens, EMA refines multi-scale fused features without aggressive channel compression, and dropout improves training-time regularization with no inference-time parameter overhead. Experiments on COCO, ExDark, BDD100K-Night, and NightOwls show that the method is most effective in low-light detection: on ExDark with YOLO11n, mAP50-95 improves from 34.39% to 36.74%, mAP50 from 56.24% to 59.27%, and Box (P) from 67.63% to 71.36%. The full YOLO11n variant uses 2.91M parameters and maintains 134.7 FPS on an RTX 2080 Ti under the tested setting. Cross-dataset and corruption experiments further indicate that the proposed modules improve localization under several nighttime domain shifts while retaining known limitations under severe noise and adverse weather. These results indicate that combining efficient global attention, multi-scale feature recalibration, and targeted regularization can improve low-light localization while keeping the detector practical for deployment.<\/jats:p>","DOI":"10.3390\/s26123909","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T14:37:42Z","timestamp":1781879862000},"page":"3909","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GE-Detection: Efficient Attention and Dropout for Low-Light Object Detection"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5252-1434","authenticated-orcid":false,"given":"Xiaochen","family":"Li","sequence":"first","affiliation":[{"name":"College of Mathematics and System Science, Xinjiang University, Huari Street, Urumqi 830017, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2659-8955","authenticated-orcid":false,"given":"Hongtian","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Mathematics and System Science, Xinjiang University, Huari Street, Urumqi 830017, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"9243","DOI":"10.1007\/s11042-022-13644-y","article-title":"Object detection using YOLO: Challenges, architectural successors, datasets and applications","volume":"82","author":"Diwan","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Liu, C., Tao, Y., Liang, J., Li, K., and Chen, Y. (2018, January 14\u201316). Object detection based on YOLO network. Proceedings of the 2018 IEEE 4th Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China.","DOI":"10.1109\/ITOEC.2018.8740604"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"012029","DOI":"10.1088\/1742-6596\/1004\/1\/012029","article-title":"Understanding of object detection based on CNN family and YOLO","volume":"1004","author":"Du","year":"2018","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_4","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Redmon, J. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_6","unstructured":"Wei, C., Wang, W., Yang, W., and Liu, J. (2018, January 3\u20136). Deep Retinex Decomposition for Low-Light Enhancement. Proceedings of the British Machine Vision Conference, Newcastle, UK."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Guo, C., Li, C., Guo, J., Loy, C.C., Hou, J., Kwong, S., and Cong, R. (2020, January 13\u201319). Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00185"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Cai, Y., Bian, H., Lin, J., Wang, H., Timofte, R., and Zhang, Y. (2023, January 1\u20136). Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.01149"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"4486","DOI":"10.1038\/s41598-024-54428-8","article-title":"A novel low light object detection method based on the YOLOv5 fusion feature enhancement","volume":"14","author":"Peng","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"21873","DOI":"10.1038\/s41598-025-07348-0","article-title":"Complex dark environment-oriented object detection method based on YOLO-AS","volume":"15","author":"Ren","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Li, Y., and Shen, L. (2025). A Frequency Domain-Enhanced Transformer for Nighttime Object Detection. Sensors, 25.","DOI":"10.3390\/s25123673"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020, January 23\u201328). End-to-end object detection with transformers. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 10\u201317). Swin transformer: Hierarchical vision transformer using shifted windows. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_14","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Lu, X., Cao, G., Yang, Y., Jiao, L., and Liu, F. (2021, January 10\u201317). ViT-YOLO: Transformer-based YOLO for object detection. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCVW54120.2021.00314"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1007\/s00371-020-01831-7","article-title":"YOLO-face: A real-time face detector","volume":"37","author":"Chen","year":"2021","journal-title":"Vis. Comput."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"102756","DOI":"10.1016\/j.dsp.2020.102756","article-title":"Faster-YOLO: An accurate and faster object detection method","volume":"102","author":"Yin","year":"2020","journal-title":"Digit. Signal Process."},{"key":"ref_18","unstructured":"Xu, S., Wang, X., Lv, W., Chang, Q., Cui, C., Deng, K., Wang, G., Dang, Q., Wei, S., and Du, Y. (2022). PP-YOLOE: An evolved version of YOLO. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"934","DOI":"10.1109\/TIP.2020.3039574","article-title":"Ratio-and-scale-aware YOLO for pedestrian detection","volume":"30","author":"Hsu","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_20","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., and Dai, J. (2021, January 3\u20137). Deformable DETR: Deformable Transformers for End-to-End Object Detection. Proceedings of the International Conference on Learning Representations, Virtual."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ouyang, D., He, S., Zhan, J., Guo, H., Huang, Z., Luo, M., and Zhang, G. (2023, January 4\u201310). Efficient Multi-Scale Attention Module with Cross-Spatial Learning. Proceedings of the ICASSP 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes, Greece.","DOI":"10.1109\/ICASSP49357.2023.10096516"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., and Hu, H. (2019, January 27\u201328). Gcnet: Non-local networks meet squeeze-excitation networks and beyond. Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, Seoul, Republic of Korea.","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","article-title":"Object detection with deep learning: A review","volume":"30","author":"Zhao","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zou, X. (2019, January 10\u201311). A review of object detection techniques. Proceedings of the 2019 International Conference on Smart Grid and Electrical Automation (ICSGEA), Xiangtan, China.","DOI":"10.1109\/ICSGEA.2019.00065"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Laroca, R., Severo, E., Zanlorensi, L.A., Oliveira, L.S., Gon\u00e7alves, G.R., Schwartz, W.R., and Menotti, D. (2018, January 8\u201313). A robust real-time automatic license plate recognition based on the YOLO detector. Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil.","DOI":"10.1109\/IJCNN.2018.8489629"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.icte.2020.07.008","article-title":"Real-time license plate detection for non-helmeted motorcyclist using YOLO","volume":"7","author":"Jamtsho","year":"2021","journal-title":"ICT Express"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Han, J., Liao, Y., Zhang, J., Wang, S., and Li, S. (2018). Target fusion detection of LiDAR and camera based on the improved YOLO algorithm. Mathematics, 6.","DOI":"10.3390\/math6100213"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Lin, J.P., and Sun, M.T. (December, January 30). A YOLO-based traffic counting system. Proceedings of the 2018 Conference on Technologies and Applications of Artificial Intelligence (TAAI), Taichung, Taiwan.","DOI":"10.1109\/TAAI.2018.00027"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"98","DOI":"10.4236\/jcc.2018.611009","article-title":"A vehicle detection method for aerial image based on YOLO","volume":"6","author":"Lu","year":"2018","journal-title":"J. Comput. Commun."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Hussain, M. (2023). YOLO-v1 to YOLO-v8, the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection. Machines, 11.","DOI":"10.3390\/machines11070677"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Huang, R., Pedoeem, J., and Chen, C. (2018, January 10\u201313). YOLO-LITE: A real-time object detection algorithm optimized for non-GPU computers. Proceedings of the 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA.","DOI":"10.1109\/BigData.2018.8621865"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Gong, B., Ergu, D., Cai, Y., and Ma, B. (2020). A method for wheat head detection based on yolov4. Res. Sq., preprint.","DOI":"10.21203\/rs.3.rs-86158\/v1"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1935","DOI":"10.1109\/ACCESS.2019.2961959","article-title":"Tinier-YOLO: A real-time object detection method for constrained environments","volume":"8","author":"Fang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_36","unstructured":"Ge, Z. (2021). Yolox: Exceeding yolo series in 2021. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Shafiee, M.J., Chywl, B., Li, F., and Wong, A. (2017). Fast YOLO: A fast you only look once system for real-time embedded object detection in video. arXiv.","DOI":"10.15353\/vsnl.v3i1.171"},{"key":"ref_38","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_39","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"Chu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_40","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014). Microsoft coco: Common objects in context. Proceedings of the Computer Vision\u2014ECCV 2014: 13th European Conference, Zurich, Switzerland, 6\u201312 September 2014, Springer. Part V 13."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.cviu.2018.10.010","article-title":"Getting to know low-light images with the exclusively dark dataset","volume":"178","author":"Loh","year":"2019","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Yu, F., Chen, H., Wang, X., Xian, W., Chen, Y., Liu, F., Madhavan, V., and Darrell, T. (2020, January 13\u201319). BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Neumann, L., Karg, M., Zhang, S., Scharfenberger, C., Piegert, E., Mistr, S., Prokofyeva, O., Thiel, R., Vedaldi, A., and Zisserman, A. (2018, January 2\u20136). NightOwls: A Pedestrians at Night Dataset. Proceedings of the Asian Conference on Computer Vision, Perth, Australia.","DOI":"10.1007\/978-3-030-20887-5_43"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Cui, Z., Qi, G.J., Zhang, Z., Gu, L., Harada, T., and You, S. (2021, January 11\u201317). Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00255"},{"key":"ref_45","unstructured":"Cui, Z., Li, K., Gu, L., Su, S., Gao, P., Jiang, Z., Qiao, Y., and Harada, T. (2022, January 21\u201324). You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction. Proceedings of the British Machine Vision Conference, London, UK."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3909\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T14:45:20Z","timestamp":1781880320000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3909"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,19]]},"references-count":45,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["s26123909"],"URL":"https:\/\/doi.org\/10.3390\/s26123909","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,19]]}}}