{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T13:33:35Z","timestamp":1776778415124,"version":"3.51.2"},"reference-count":48,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T00:00:00Z","timestamp":1766534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Face detection is an important task in the field of computer vision and is widely applied in various applications. However, in open and complex scenes with dense faces, occlusions, and image degradation, small face detection still faces significant challenges due to the extremely small target scale, difficult localization, and severe background interference. To address these issues, this paper proposes a small face detector for open complex scenes, SFE-DETR, which aims to simultaneously improve detection accuracy and computational efficiency. The backbone network of the model adopts an inverted residual shift convolution and dilated reparameterization structure, which enhances shallow features and enables deep feature self-adaptation, thereby better preserving small-scale information and reducing the number of parameters. Additionally, a multi-head multi-scale self-attention mechanism is introduced to fuse multi-scale convolutional features with channel-wise weighting, capturing fine-grained facial features while suppressing background noise. Moreover, a redesigned SFE-FPN introduces high-resolution layers and incorporates a novel feature fusion module consisting of local, large-scale, and global branches, efficiently aggregating multi-level features and significantly improving small face detection performance. Experimental results on two challenging small face detection datasets show that SFE-DETR reduces parameters by 28.1% compared to the original RT-DETR-R18 model, achieving a mAP50 of 94.7% and AP-s of 42.1% on the SCUT-HEAD dataset, and a mAP50 of 86.3% on the WIDER FACE (Hard) subset. These results demonstrate that SFE-DETR achieves optimal detection performance among models of the same scale while maintaining efficiency.<\/jats:p>","DOI":"10.3390\/s26010125","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T16:41:19Z","timestamp":1766594479000},"page":"125","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SFE-DETR: An Enhanced Transformer-Based Face Detector for Small Target Faces in Open Complex Scenes"],"prefix":"10.3390","volume":"26","author":[{"given":"Chenhao","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueming","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyan","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"110714","DOI":"10.1016\/j.patcog.2024.110714","article-title":"YOLO-facev2: A scale and occlusion aware face detector","volume":"155","author":"Yu","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Quiles-Cucarella, E., Cano-Bernet, J., Santos-Fern\u00e1ndez, L., Rold\u00e1n-Blay, C., and Rold\u00e1n-Porta, C. (2024). Multi-index driver drowsiness detection method based on driver\u2019s facial recognition using haar features and histograms of oriented gradients. Sensors, 24.","DOI":"10.3390\/s24175683"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Cao, J., Song, C., Peng, S., Song, S., Zhang, X., Shao, Y., and Xiao, F. (2020). Pedestrian detection algorithm for intelligent vehicles in complex scenarios. Sensors, 20.","DOI":"10.3390\/s20133646"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., and Girshick, R. (2017, January 22\u201329). Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., and Berg, A.C. (2016, January 11\u201314). Ssd: Single shot multibox detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (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_9","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017). Attention is all you need. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_10","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_11","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., and Chen, J. (2024, January 17\u201321). DETRs beat YOLOs on real-time object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref_12","unstructured":"Song, H., Sun, D., Chun, S., Jampani, V., Han, D., Heo, B., Kim, W., and Yang, M.-H. (2021). Vidt: An efficient and effective fully transformer-based object detector. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"103620","DOI":"10.1016\/j.jvcir.2022.103620","article-title":"Improving small objects detection using transformer","volume":"89","author":"Dubey","year":"2022","journal-title":"J. Vis. Commun. Image Represent."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wang, S., Jiang, H., Yang, J., Ma, X., and Chen, J. (2024). Amfef-DETR: An end-to-end adaptive multi-scale feature extraction and fusion object detection network based on UAV aerial images. Drones, 8.","DOI":"10.3390\/drones8100523"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Tong, Y., Ye, H., Yang, J., and Yang, X. (2025). ACD-DETR: Adaptive Cross-Scale Detection Transformer for Small Object Detection in UAV Imagery. Sensors, 25.","DOI":"10.3390\/s25175556"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1968","DOI":"10.1109\/TMM.2021.3074273","article-title":"Extended feature pyramid network for small object detection","volume":"24","author":"Deng","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Chen, J., Kao, S.-h., He, H., Zhuo, W., Wen, S., Lee, C.-H., and Chan, S.-H.G. (2023, January 18\u201322). Run, don\u2019t walk: Chasing higher FLOPS for faster neural networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhu, X., Lei, Z., Shi, H., Wang, X., and Li, S.Z. (2017, January 1\u20134). Faceboxes: A cpu real-time face detector with high accuracy. Proceedings of the 2017 IEEE International Joint Conference on Biometrics (IJCB), Denver, CO, USA.","DOI":"10.1109\/BTAS.2017.8272675"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, Y., Wang, C., Tai, Y., Qian, J., Yang, J., Wang, C., Li, J., and Huang, F. (2019, January 16\u201320). DSFD: Dual shot face detector. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00520"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhu, C., Tao, R., Luu, K., and Savvides, M. (2018, January 18\u201322). Seeing small faces from robust anchor\u2019s perspective. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00538"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Najibi, M., Samangouei, P., Chellappa, R., and Davis, L.S. (2017, January 22\u201329). Ssh: Single stage headless face detector. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.522"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1250","DOI":"10.1109\/TPAMI.2022.3152562","article-title":"Unsupervised face detection in the dark","volume":"45","author":"Wang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Qi, D., Tan, W., Yao, Q., and Liu, J. (2022, January 23\u201327). YOLO5Face: Why reinventing a face detector. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-25072-9_15"},{"key":"ref_24","unstructured":"Liu, S., Li, F., Zhang, H., Yang, X., Qi, X., Su, H., Zhu, J., and Zhang, L. (2022). Dab-DETR: Dynamic anchor boxes are better queries for DETR. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., and Zhang, L. (2022, January 19\u201324). Dn-DETR: Accelerate DETR training by introducing query denoising. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Chen, Q., Chen, X., Wang, J., Zhang, S., Yao, K., Feng, H., Han, J., Ding, E., Zeng, G., and Wang, J. (2023, January 2\u20133). Group DETR: Fast DETR training with group-wise one-to-many assignment. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.00610"},{"key":"ref_27","unstructured":"Yao, Z., Ai, J., Li, B., and Zhang, C. (2021). Efficient DETR: Improving end-to-end object detector with dense prior. arXiv."},{"key":"ref_28","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., and Dai, J. (2020). Deformable DETR: Deformable transformers for end-to-end object detection. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Meng, D., Chen, X., Fan, Z., Zeng, G., Li, H., Yuan, Y., Sun, L., and Wang, J. (2021, January 10\u201317). Conditional DETR for fast training convergence. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref_30","unstructured":"Wang, Y., Zhang, X., Yang, T., and Sun, J. (March, January 22). Anchor DETR: Query design for transformer-based detector. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual."},{"key":"ref_31","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., and Shum, H.-Y. (2022). Dino: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Sunkara, R., and Luo, T. (2022, January 19\u201323). No more strided convolutions or pooling: A new CNN building block for low-resolution images and small objects. Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Grenoble, France.","DOI":"10.1007\/978-3-031-26409-2_27"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Wang, S., Chen, D., Xiang, J., and Zhang, C. (2024). A Deep-Learning-Based Detection Method for Small Target Tomato Pests in Insect Traps. Agronomy, 14.","DOI":"10.3390\/agronomy14122887"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Liu, Z., Sun, C., and Wang, X. (2024). DST-DETR: Image Dehazing RT-DETR for safety helmet detection in foggy weather. Sensors, 24.","DOI":"10.3390\/s24144628"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21\u201326). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Peng, D., Sun, Z., Chen, Z., Cai, Z., Xie, L., and Jin, L. (2018, January 20\u201324). Detecting heads using feature refine net and cascaded multi-scale architecture. Proceedings of the 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China.","DOI":"10.1109\/ICPR.2018.8545068"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Yang, S., Luo, P., Loy, C.-C., and Tang, X. (2016, January 27\u201330). Wider face: A face detection benchmark. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.596"},{"key":"ref_38","unstructured":"Powers, D.M. (2020). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., and Dai, J. (2019, January 16\u201320). Deformable convnets v2: More deformable, better results. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Qi, Y., He, Y., Qi, X., Zhang, Y., and Yang, G. (2023, January 2\u20133). Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.00558"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, X., Li, J., Liu, L., Xue, Z., Zhang, B., Jiang, Z., Huang, T., Wang, Y., and Wang, C. (2023, January 2\u20133). Rethinking mobile block for efficient attention-based models. Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"9528","DOI":"10.1109\/TNNLS.2022.3151138","article-title":"DualConv: Dual convolutional kernels for lightweight deep neural networks","volume":"34","author":"Zhong","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_43","first-page":"107984","article-title":"YOLOv10: Real-time end-to-end object detection","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_44","unstructured":"Khanam, R., and Hussain, M. (2024). YOLOv11: An overview of the key architectural enhancements. arXiv."},{"key":"ref_45","unstructured":"Wang, H., Li, Z., Ji, X., and Wang, Y. (2017). Face r-cnn. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Ververas, E., Kotsia, I., and Zafeiriou, S. (2020, January 14\u201319). Retinaface: Single-shot multi-level face localisation in the wild. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref_47","unstructured":"Zhu, Y., Cai, H., Zhang, S., Wang, C., and Xiong, Y. (2020). Tinaface: Strong but simple baseline for face detection. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Liu, L., Wang, G., and Miao, Q. (2024). ADYOLOv5-Face: An Enhanced YOLO-Based Face Detector for Small Target Faces. Electronics, 13.","DOI":"10.3390\/electronics13214184"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/125\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T05:12:09Z","timestamp":1766725929000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/125"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,24]]},"references-count":48,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26010125"],"URL":"https:\/\/doi.org\/10.3390\/s26010125","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,24]]}}}