{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T02:38:43Z","timestamp":1778553523339,"version":"3.51.4"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T00:00:00Z","timestamp":1754956800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T00:00:00Z","timestamp":1754956800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276013"],"award-info":[{"award-number":["62276013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s00138-025-01729-1","type":"journal-article","created":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T15:30:25Z","timestamp":1755012625000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A lightweight and generalizable detection enhancement method using segmentation feedback"],"prefix":"10.1007","volume":"36","author":[{"given":"Song","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zi\u2019ang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,12]]},"reference":[{"issue":"18","key":"1729_CR1","doi-asserted-by":"publisher","first-page":"8972","DOI":"10.3390\/app12188972","volume":"12","author":"M Shafiq","year":"2022","unstructured":"Shafiq, M., Gu, Z.: Deep residual learning for image recognition: a survey. Appl. Sci. 12(18), 8972 (2022)","journal-title":"Appl. Sci."},{"issue":"1","key":"1729_CR2","first-page":"1","volume":"16","author":"L Zhao","year":"2022","unstructured":"Zhao, L., Wang, L.: A new lightweight network based on mobilenetv3. KSII Trans. Int. Inf. Syst. 16(1), 1\u201315 (2022)","journal-title":"KSII Trans. Int. Inf. Syst."},{"key":"1729_CR3","doi-asserted-by":"crossref","unstructured":"Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., Sun, J.: Detnet: Design backbone for object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 334\u2013350 (2018)","DOI":"10.1007\/978-3-030-01240-3_21"},{"key":"1729_CR4","doi-asserted-by":"crossref","unstructured":"Qin, D., Leichner, C., Delakis, M., Fornoni, M., Luo, S., Yang, F., Wang, W., Banbury, C., Ye, C., Akin, B., et al.: Mobilenetv4: Universal models for the mobile ecosystem. In: European Conference on Computer Vision, pp. 78\u201396. Springer (2025)","DOI":"10.1007\/978-3-031-73661-2_5"},{"key":"1729_CR5","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"issue":"21","key":"1729_CR6","doi-asserted-by":"publisher","first-page":"30685","DOI":"10.1007\/s11042-022-11940-1","volume":"81","author":"Y Luo","year":"2022","unstructured":"Luo, Y., Cao, X., Zhang, J., Guo, J., Shen, H., Wang, T., Feng, Q.: Ce-fpn: enhancing channel information for object detection. Multimed. Tools Appl. 81(21), 30685\u201330704 (2022)","journal-title":"Multimed. Tools Appl."},{"key":"1729_CR7","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"1729_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109878","volume":"145","author":"W Lin","year":"2024","unstructured":"Lin, W., Chu, J., Leng, L., Miao, J., Wang, L.: Feature disentanglement in one-stage object detection. Pattern Recogn. 145, 109878 (2024)","journal-title":"Pattern Recogn."},{"key":"1729_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009). IEEE Computer Society","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1729_CR10","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607 (2020). PMLR"},{"issue":"3","key":"1729_CR11","doi-asserted-by":"publisher","first-page":"1327","DOI":"10.1109\/TPAMI.2022.3201576","volume":"46","author":"Y Chen","year":"2022","unstructured":"Chen, Y., Mancini, M., Zhu, X., Akata, Z.: Semi-supervised and unsupervised deep visual learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(3), 1327\u20131347 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1729_CR12","first-page":"8799","volume":"35","author":"A Bardes","year":"2022","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: Vicregl: self-supervised learning of local visual features. Adv. Neural. Inf. Process. Syst. 35, 8799\u20138810 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1729_CR13","first-page":"22682","volume":"34","author":"F Wei","year":"2021","unstructured":"Wei, F., Gao, Y., Wu, Z., Hu, H., Lin, S.: Aligning pretraining for detection via object-level contrastive learning. Adv. Neural. Inf. Process. Syst. 34, 22682\u201322694 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1729_CR14","doi-asserted-by":"crossref","unstructured":"Li, M., Wu, J., Wang, X., Chen, C., Qin, J., Xiao, X., Wang, R., Zheng, M., Pan, X.: Aligndet: aligning pre-training and fine-tuning in object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6866\u20136876 (2023)","DOI":"10.1109\/ICCV51070.2023.00632"},{"key":"1729_CR15","doi-asserted-by":"publisher","first-page":"4259","DOI":"10.1007\/s10462-019-09792-7","volume":"53","author":"M Zhang","year":"2020","unstructured":"Zhang, M., Zhou, Y., Zhao, J., Man, Y., Liu, B., Yao, R.: A survey of semi-and weakly supervised semantic segmentation of images. Artif. Intell. Rev. 53, 4259\u20134288 (2020)","journal-title":"Artif. Intell. Rev."},{"issue":"1","key":"1729_CR16","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1109\/TII.2023.3268479","volume":"20","author":"X Liu","year":"2023","unstructured":"Liu, X., Miao, X., Jiang, H., Chen, J., Wu, M., Chen, Z.: Tower masking mim: a self-supervised pretraining method for power line inspection. IEEE Trans. Ind. Inf. 20(1), 513\u2013523 (2023)","journal-title":"IEEE Trans. Industr. Inf."},{"key":"1729_CR17","doi-asserted-by":"crossref","unstructured":"Yang, C., Huang, Z., Wang, N.: Querydet: Cascaded sparse query for accelerating high-resolution small object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13668\u201313677 (2022)","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"1729_CR18","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"1729_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: Proceedings of Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Part V 13, pp. 740\u2013755 (2014). Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1729_CR20","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vis. 88, 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"key":"1729_CR21","doi-asserted-by":"publisher","unstructured":"Gomaa, A., M.Abdelwahab, M., Abo-Zahhad, M.: Real-time algorithm for simultaneous vehicle detection and tracking in aerial view videos. In: 2018 IEEE 61st International Midwest Symposium on Circuits and Systems (MWSCAS), pp. 222\u2013225 (2018). https:\/\/doi.org\/10.1109\/MWSCAS.2018.8624022","DOI":"10.1109\/MWSCAS.2018.8624022"},{"issue":"35","key":"1729_CR22","doi-asserted-by":"publisher","first-page":"26023","DOI":"10.1007\/s11042-020-09242-5","volume":"79","author":"A Gomaa","year":"2020","unstructured":"Gomaa, A., Abdelwahab, M.M., Abo-Zahhad, M.: Efficient vehicle detection and tracking strategy in aerial videos by employing morphological operations and feature points motion analysis. Multimed. Tools Appl. 79(35), 26023\u201326043 (2020)","journal-title":"Multimed. Tools Appl."},{"key":"1729_CR23","doi-asserted-by":"publisher","unstructured":"Gomaa, A., Afifi, A., Abdalrazik, A.: A dual-band wide axial-ratio beamwidth circularly-polarized antenna with v-shaped slot for l2\/l5 gnss applications. In: 2024 6th Novel Intelligent and Leading Emerging Sciences Conference (NILES), pp. 119\u2013122 (2024). https:\/\/doi.org\/10.1109\/NILES63360.2024.10753263","DOI":"10.1109\/NILES63360.2024.10753263"},{"issue":"8","key":"1729_CR24","doi-asserted-by":"publisher","first-page":"3779","DOI":"10.1007\/s11276-022-03093-8","volume":"28","author":"A Abdalrazik","year":"2022","unstructured":"Abdalrazik, A., Gomaa, A., Kishk, A.A.: A wide axial-ratio beamwidth circularly-polarized oval patch antenna with sunlight-shaped slots for gnss and wimax applications. Wireless Netw. 28(8), 3779\u20133786 (2022)","journal-title":"Wireless Netw."},{"issue":"7","key":"1729_CR25","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1017\/S175907872400045X","volume":"16","author":"A Abdalrazik","year":"2024","unstructured":"Abdalrazik, A., Gomaa, A., Afifi, A.: Multiband circularly-polarized stacked elliptical patch antenna with eye-shaped slot for gnss applications. Int. J. Microw. Wirel. Technol. 16(7), 1229\u20131235 (2024). https:\/\/doi.org\/10.1017\/S175907872400045X","journal-title":"Int. J. Microw. Wirel. Technol."},{"key":"1729_CR26","doi-asserted-by":"publisher","unstructured":"Salem, M., Gomaa, A., Tsurusaki, N.: Detection of earthquake-induced building damages using remote sensing data and deep learning: a case study of Mashiki town, Japan. In: IGARSS 2023\u20132023 IEEE International Geoscience and Remote Sensing Symposium, pp. 2350\u20132353 (2023). https:\/\/doi.org\/10.1109\/IGARSS52108.2023.10282550","DOI":"10.1109\/IGARSS52108.2023.10282550"},{"key":"1729_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918","volume":"89","author":"MA Mazurowski","year":"2023","unstructured":"Mazurowski, M.A., Dong, H., Gu, H., Yang, J., Konz, N., Zhang, Y.: Segment anything model for medical image analysis: an experimental study. Med. Image Anal. 89, 102918 (2023)","journal-title":"Med. Image Anal."},{"key":"1729_CR28","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"1729_CR29","first-page":"1137","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 1137\u20131149 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1729_CR30","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1016\/j.neucom.2020.06.128","volume":"453","author":"F Chen","year":"2021","unstructured":"Chen, F., Wu, F., Xu, J., Gao, G., Ge, Q., Jing, X.-Y.: Adaptive deformable convolutional network. Neurocomputing 453, 853\u2013864 (2021)","journal-title":"Neurocomputing"},{"issue":"9","key":"1729_CR31","doi-asserted-by":"publisher","first-page":"6324","DOI":"10.1109\/TCSVT.2022.3167114","volume":"32","author":"D Wang","year":"2022","unstructured":"Wang, D., Shang, K., Wu, H., Wang, C.: Decoupled r-cnn: sensitivity-specific detector for higher accurate localization. IEEE Trans. Circuits Syst. Video Technol. 32(9), 6324\u20136336 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1729_CR32","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"issue":"10","key":"1729_CR33","doi-asserted-by":"publisher","first-page":"8275","DOI":"10.1007\/s00521-021-05978-9","volume":"34","author":"P Hurtik","year":"2022","unstructured":"Hurtik, P., Molek, V., Hula, J., Vajgl, M., Vlasanek, P., Nejezchleba, T.: Poly-yolo: higher speed, more precise detection and instance segmentation for yolov3. Neural Comput. Appl. 34(10), 8275\u20138290 (2022)","journal-title":"Neural Comput. Appl."},{"key":"1729_CR34","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"issue":"6","key":"1729_CR35","doi-asserted-by":"publisher","first-page":"255","DOI":"10.3390\/wevj15060255","volume":"15","author":"A Gomaa","year":"2024","unstructured":"Gomaa, A., Abdalrazik, A.: Novel deep learning domain adaptation approach for object detection using semi-self building dataset and modified yolov4. World Electric Vehicle J. 15(6), 255 (2024)","journal-title":"World Electric Vehicle J."},{"key":"1729_CR36","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"1729_CR37","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1729_CR38","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: Fcos: Fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"1729_CR39","doi-asserted-by":"crossref","unstructured":"Gomaa, A., Saad, O.M.: Residual channel-attention (RCA) network for remote sensing image scene classification. Multimed Tools Appl. pp. 1\u201325 (2025)","DOI":"10.1007\/s11042-024-20546-8"},{"issue":"02","key":"1729_CR40","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","volume":"42","author":"K He","year":"2020","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask r-cnn. IEEE Trans. Pattern Anal. Mach. Intell. 42(02), 386\u2013397 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"1729_CR41","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","volume":"43","author":"Z Cai","year":"2019","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: high quality object detection and instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1483\u20131498 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1729_CR42","doi-asserted-by":"publisher","first-page":"2078","DOI":"10.1109\/TIP.2019.2947806","volume":"29","author":"H Zhang","year":"2019","unstructured":"Zhang, H., Tian, Y., Wang, K., Zhang, W., Wang, F.-Y.: Mask ssd: an effective single-stage approach to object instance segmentation. IEEE Trans. Image Process. 29, 2078\u20132093 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"1729_CR43","doi-asserted-by":"crossref","unstructured":"Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: Yolact: Real-time instance segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9157\u20139166 (2019)","DOI":"10.1109\/ICCV.2019.00925"},{"key":"1729_CR44","doi-asserted-by":"crossref","unstructured":"Chen, K., Pang, J., Wang, J., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Shi, J., Ouyang, W., et al.: Hybrid task cascade for instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4974\u20134983 (2019)","DOI":"10.1109\/CVPR.2019.00511"},{"key":"1729_CR45","unstructured":"Fu, C.-Y., Shvets, M., Berg, A.C.: Retinamask: Learning to predict masks improves state-of-the-art single-shot detection for free. arXiv preprint arXiv:1901.03353 (2019)"},{"key":"1729_CR46","doi-asserted-by":"crossref","unstructured":"Wang, X., Kong, T., Shen, C., Jiang, Y., Li, L.: Solo: Segmenting objects by locations. In: Proceedings of 16th European Conference on Computer Vision\u2013ECCV 2020, Glasgow, UK, August 23\u201328, 2020, Part XVIII 16, pp. 649\u2013665 (2020). Springer","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"1729_CR47","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Wang, X., Chen, H.: Boxinst: High-performance instance segmentation with box annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5443\u20135452 (2021)","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"1729_CR48","doi-asserted-by":"publisher","first-page":"4259","DOI":"10.1007\/s10462-019-09792-7","volume":"53","author":"M Zhang","year":"2020","unstructured":"Zhang, M., Zhou, Y., Zhao, J., Man, Y., Liu, B., Yao, R.: A survey of semi-and weakly supervised semantic segmentation of images. Artif. Intell. Rev. 53, 4259\u20134288 (2020)","journal-title":"Artif. Intell. Rev."},{"key":"1729_CR49","doi-asserted-by":"crossref","unstructured":"Khoreva, A., Benenson, R., Hosang, J., Hein, M., Schiele, B.: Simple does it: Weakly supervised instance and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 876\u2013885 (2017)","DOI":"10.1109\/CVPR.2017.181"},{"issue":"1","key":"1729_CR50","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1109\/TPAMI.2016.2537320","volume":"39","author":"J Pont-Tuset","year":"2016","unstructured":"Pont-Tuset, J., Arbelaez, P., Barron, J.T., Marques, F., Malik, J.: Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE Trans. Pattern Anal. Mach. Intell. 39(1), 128\u2013140 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"1729_CR51","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1145\/1015706.1015720","volume":"23","author":"C Rother","year":"2004","unstructured":"Rother, C., Kolmogorov, V., Blake, A.: Grabcut interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23(3), 309\u2013314 (2004)","journal-title":"ACM Trans. Graph."},{"key":"1729_CR52","doi-asserted-by":"crossref","unstructured":"Song, C., Huang, Y., Ouyang, W., Wang, L.: Box-driven class-wise region masking and filling rate guided loss for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3136\u20133145 (2019)","DOI":"10.1109\/CVPR.2019.00325"},{"key":"1729_CR53","doi-asserted-by":"crossref","unstructured":"Kulharia, V., Chandra, S., Agrawal, A., Torr, P., Tyagi, A.: Box2seg: attention weighted loss and discriminative feature learning for weakly supervised segmentation. In: Proceedings of 16th European Conference of Computer Vision\u2013ECCV 2020: Glasgow, UK, August 23\u201328, 2020, Part XXVII 16, pp. 290\u2013308 (2020). Springer","DOI":"10.1007\/978-3-030-58583-9_18"},{"key":"1729_CR54","doi-asserted-by":"crossref","unstructured":"Oh, Y., Kim, B., Ham, B.: Background-aware pooling and noise-aware loss for weakly-supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6913\u20136922 (2021)","DOI":"10.1109\/CVPR46437.2021.00684"},{"key":"1729_CR55","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: 2011 International Conference on Computer Vision, pp. 991\u2013998 (2011). IEEE","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"1729_CR56","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al.: Pytorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"1729_CR57","doi-asserted-by":"publisher","unstructured":"Jocher, G.: YOLOv5 by Ultralytics. https:\/\/doi.org\/10.5281\/zenodo.3908559. https:\/\/github.com\/ultralytics\/yolov5","DOI":"10.5281\/zenodo.3908559"},{"key":"1729_CR58","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"1729_CR59","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229 (2020). Springer","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1729_CR60","unstructured":"Xu, S., Wang, X., Lv, W., Chang, Q., Cui, C., Deng, K., Wang, G., Dang, Q., Wei, S., Du, Y., et al.: Pp-yoloe: an evolved version of yolo. arXiv preprint arXiv:2203.16250 (2022)"},{"key":"1729_CR61","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Xu, H., Liu, S., Zhang, L., Ni, L.M., Shum, H.-Y.: Mask dino: towards a unified transformer-based framework for object detection and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3041\u20133050 (2023)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"1729_CR62","unstructured":"Chen, Z., Duan, Y., Wang, W., He, J., Lu, T., Dai, J., Qiao, Y.: Vision transformer adapter for dense predictions. arXiv preprint arXiv:2205.08534 (2022)"},{"key":"1729_CR63","unstructured":"Lyu, C., Zhang, W., Huang, H., Zhou, Y., Wang, Y., Liu, Y., Zhang, S., Chen, K.: Rtmdet: an empirical study of designing real-time object detectors. arXiv preprint arXiv:2212.07784 (2022)"},{"key":"1729_CR64","doi-asserted-by":"crossref","unstructured":"Zhao, X., Liang, S., Wei, Y.: Pseudo mask augmented object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4061\u20134070 (2018)","DOI":"10.1109\/CVPR.2018.00427"},{"key":"1729_CR65","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.neucom.2019.01.018","volume":"335","author":"T Zhang","year":"2019","unstructured":"Zhang, T., Hao, L.-Y., Guo, G.: A feature enriching object detection framework with weak segmentation loss. Neurocomputing 335, 72\u201380 (2019)","journal-title":"Neurocomputing"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-025-01729-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-025-01729-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-025-01729-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T14:58:11Z","timestamp":1757689091000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-025-01729-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,12]]},"references-count":65,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["1729"],"URL":"https:\/\/doi.org\/10.1007\/s00138-025-01729-1","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,12]]},"assertion":[{"value":"22 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"111"}}