{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T14:40:37Z","timestamp":1777560037191,"version":"3.51.4"},"reference-count":35,"publisher":"SAGE Publications","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIC"],"published-print":{"date-parts":[[2024,3,21]]},"abstract":"<jats:p>The majority of existing rotating target detectors inherit the horizontal detection paradigm and design the rotational regression loss based on the inductive paradigm. But the loss design limitation of the inductive paradigm makes these detectors hardly detect effectively tiny targets with high accuracy, particularly for large-aspect-ratio objects. Therefore, in view of the fact that horizontal detection is a special scenario of rotating target detection and based on the relationship between rotational and horizontal detection, we shift from an inductive to a deductive paradigm of design to develop a new regression loss function named Gauss\u2013Wasserstein scattering (GWS). First, the rotating bounding box is transformed into a two-dimensional Gaussian distribution, and then the regression losses between Gaussian distributions are calculated as the Wasserstein scatter; By analyzing the gradient of centroid regression, centroid regression is shown to be able to adjust gradients dynamically based on object characteristics, and small targets requiring high accuracy detection rely on this mechanism, and more importantly, it is further demonstrated that GWS is scale-invariant while possessing an explicit regression logic. The method is performed on a large public remote sensing dataset DOTA and two popular detectors and achieves a large accuracy improvement in both large aspect ratio targets and small targets detection compared to similar methods.<\/jats:p>","DOI":"10.3233\/aic-230135","type":"journal-article","created":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T11:25:12Z","timestamp":1702380312000},"page":"169-183","source":"Crossref","is-referenced-by-count":2,"title":["GWS: Rotation object detection in aerial remote sensing images based on Gauss\u2013Wasserstein scattering"],"prefix":"10.1177","volume":"37","author":[{"given":"Ling","family":"Gan","sequence":"first","affiliation":[{"name":"School of Computer, Chongqing University of Posts and Telecommunications, Chongqing, China"}]},{"given":"Xiaodong","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Computer, Chongqing University of Posts and Telecommunications, Chongqing, China"}]},{"given":"Liuhui","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"}]}],"member":"179","reference":[{"key":"10.3233\/AIC-230135_ref1","doi-asserted-by":"crossref","unstructured":"S.M.\u00a0Azimi, E.\u00a0Vig, R.\u00a0Bahmanyar, M.\u00a0K\u00f6rner and P.\u00a0Reinartz, Towards multi-class object detection in unconstrained remote sensing imagery, in: Asian Conference on Computer Vision, Springer, 2018, pp.\u00a0150\u2013165.","DOI":"10.1007\/978-3-030-20893-6_10"},{"key":"10.3233\/AIC-230135_ref2","doi-asserted-by":"crossref","unstructured":"N.\u00a0Carion, F.\u00a0Massa, G.\u00a0Synnaeve, N.\u00a0Usunier, A.\u00a0Kirillov and S.\u00a0Zagoruyko, End-to-end object detection with transformers, in: European Conference on Computer Vision, Springer, 2020, pp.\u00a0213\u2013229.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"10.3233\/AIC-230135_ref3","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Chen, K.\u00a0Chen, W.\u00a0Lin, J.\u00a0See, H.\u00a0Yu, Y.\u00a0Ke and C.\u00a0Yang, Piou loss: Towards accurate oriented object detection in complex environments, in: European Conference on Computer Vision, Springer, 2020, pp.\u00a0195\u2013211.","DOI":"10.1007\/978-3-030-58558-7_12"},{"key":"10.3233\/AIC-230135_ref4","unstructured":"J.\u00a0Dai, Y.\u00a0Li, K.\u00a0He and J.\u00a0Sun, R-fcn: Object detection via region-based fully convolutional networks, in: Advances in Neural Information Processing Systems, Vol.\u00a029, 2016."},{"key":"10.3233\/AIC-230135_ref5","doi-asserted-by":"crossref","unstructured":"J.\u00a0Ding, N.\u00a0Xue, Y.\u00a0Long, G.-S.\u00a0Xia and Q.\u00a0Lu, Learning RoI transformer for oriented object detection in aerial images, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp.\u00a02849\u20132858.","DOI":"10.1109\/CVPR.2019.00296"},{"key":"10.3233\/AIC-230135_ref6","doi-asserted-by":"crossref","unstructured":"R.\u00a0Girshick, Fast r-cnn, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp.\u00a01440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"issue":"2","key":"10.3233\/AIC-230135_ref7","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1307\/mmj\/1029003026","article-title":"A class of Wasserstein metrics for probability distributions","volume":"31","author":"Givens","year":"1984","journal-title":"Michigan Mathematical Journal"},{"key":"10.3233\/AIC-230135_ref8","first-page":"1","article-title":"Align deep features for oriented object detection","volume":"60","author":"Han","year":"2021","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.3233\/AIC-230135_ref9","doi-asserted-by":"crossref","unstructured":"K.\u00a0He, X.\u00a0Zhang, S.\u00a0Ren and J.\u00a0Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp.\u00a0770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1007","key":"10.3233\/AIC-230135_ref10","first-page":"453","article-title":"An invariant form for the prior probability in estimation problems","volume":"186","author":"Jeffreys","year":"1946","journal-title":"Proceedings of the Royal Society of London. Series A. Mathematical and Physical Sciences"},{"key":"10.3233\/AIC-230135_ref12","doi-asserted-by":"crossref","unstructured":"T.-Y.\u00a0Lin, P.\u00a0Doll\u00e1r, R.\u00a0Girshick, K.\u00a0He, B.\u00a0Hariharan and S.\u00a0Belongie, Feature pyramid networks for object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp.\u00a02117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"10.3233\/AIC-230135_ref13","doi-asserted-by":"crossref","unstructured":"T.-Y.\u00a0Lin, P.\u00a0Goyal, R.\u00a0Girshick, K.\u00a0He and P.\u00a0Doll\u00e1r, Focal loss for dense object detection, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp.\u00a02980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"10.3233\/AIC-230135_ref14","doi-asserted-by":"crossref","unstructured":"W.\u00a0Liu, D.\u00a0Anguelov, D.\u00a0Erhan, C.\u00a0Szegedy, S.\u00a0Reed, C.-Y.\u00a0Fu and A.C.\u00a0Berg, Ssd: Single shot multibox detector, in: European Conference on Computer Vision, Springer, 2016, pp.\u00a021\u201337.","DOI":"10.1007\/978-3-319-46448-0_2"},{"issue":"11","key":"10.3233\/AIC-230135_ref15","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1109\/TMM.2018.2818020","article-title":"Arbitrary-oriented scene text detection via rotation proposals","volume":"20","author":"Ma","year":"2018","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.3233\/AIC-230135_ref16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2021.3095186","article-title":"CFC-Net: A critical feature capturing network for arbitrary-oriented object detection in remote-sensing images","volume":"60","author":"Ming","year":"2021","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"issue":"14","key":"10.3233\/AIC-230135_ref17","doi-asserted-by":"publisher","first-page":"2664","DOI":"10.3390\/rs13142664","article-title":"Sparse label assignment for oriented object detection in aerial images","volume":"13","author":"Ming","year":"2021","journal-title":"Remote Sensing"},{"key":"10.3233\/AIC-230135_ref18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2021.3115110","article-title":"Optimization for arbitrary-oriented object detection via representation invariance loss","volume":"19","author":"Ming","year":"2021","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"10.3233\/AIC-230135_ref19","doi-asserted-by":"crossref","unstructured":"Q.\u00a0Ming, Z.\u00a0Zhou, L.\u00a0Miao, H.\u00a0Zhang and L.\u00a0Li, Dynamic anchor learning for arbitrary-oriented object detection, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol.\u00a035, 2021, pp.\u00a02355\u20132363.","DOI":"10.1609\/aaai.v35i3.16336"},{"key":"10.3233\/AIC-230135_ref20","doi-asserted-by":"crossref","unstructured":"X.\u00a0Pan, Y.\u00a0Ren, K.\u00a0Sheng, W.\u00a0Dong, H.\u00a0Yuan, X.\u00a0Guo, C.\u00a0Ma and C.\u00a0Xu, Dynamic refinement network for oriented and densely packed object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp.\u00a011207\u201311216.","DOI":"10.1109\/CVPR42600.2020.01122"},{"key":"10.3233\/AIC-230135_ref21","doi-asserted-by":"crossref","unstructured":"W.\u00a0Qian, X.\u00a0Yang, S.\u00a0Peng, J.\u00a0Yan and Y.\u00a0Guo, Learning modulated loss for rotated object detection, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol.\u00a035, 2021, pp.\u00a02458\u20132466.","DOI":"10.1609\/aaai.v35i3.16347"},{"key":"10.3233\/AIC-230135_ref22","doi-asserted-by":"crossref","unstructured":"J.\u00a0Redmon, S.\u00a0Divvala, R.\u00a0Girshick and A.\u00a0Farhadi, You only look once: Unified, real-time object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp.\u00a0779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"10.3233\/AIC-230135_ref23","unstructured":"S.\u00a0Ren, K.\u00a0He, R.\u00a0Girshick and J.\u00a0Sun, Faster r-cnn: Towards real-time object detection with region proposal networks, in: Advances in Neural Information Processing Systems, Vol.\u00a028, 2015."},{"key":"10.3233\/AIC-230135_ref24","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Tian, C.\u00a0Shen, H.\u00a0Chen and T.\u00a0He, Fcos: Fully convolutional one-stage object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp.\u00a09627\u20139636.","DOI":"10.1109\/ICCV.2019.00972"},{"key":"10.3233\/AIC-230135_ref25","unstructured":"C.\u00a0Villani, Optimal Transport: Old and New, Springer Science & Business Media, 2008."},{"key":"10.3233\/AIC-230135_ref26","doi-asserted-by":"crossref","unstructured":"G.-S.\u00a0Xia, X.\u00a0Bai, J.\u00a0Ding, Z.\u00a0Zhu, S.\u00a0Belongie, J.\u00a0Luo, M.\u00a0Datcu, M.\u00a0Pelillo and L.\u00a0Zhang, DOTA: A large-scale dataset for object detection in aerial images, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp.\u00a03974\u20133983.","DOI":"10.1109\/CVPR.2018.00418"},{"key":"10.3233\/AIC-230135_ref27","doi-asserted-by":"crossref","unstructured":"X.\u00a0Yang, L.\u00a0Hou, Y.\u00a0Zhou, W.\u00a0Wang and J.\u00a0Yan, Dense label encoding for boundary discontinuity free rotation detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp.\u00a015819\u201315829.","DOI":"10.1109\/CVPR46437.2021.01556"},{"issue":"1","key":"10.3233\/AIC-230135_ref28","doi-asserted-by":"publisher","first-page":"132","DOI":"10.3390\/rs10010132","article-title":"Automatic ship detection in remote sensing images from Google Earth of complex scenes based on multiscale rotation dense feature pyramid networks","volume":"10","author":"Yang","year":"2018","journal-title":"Remote Sensing"},{"key":"10.3233\/AIC-230135_ref29","doi-asserted-by":"publisher","first-page":"50839","DOI":"10.1109\/ACCESS.2018.2869884","article-title":"Position detection and direction prediction for arbitrary-oriented ships via multitask rotation region convolutional neural network","volume":"6","author":"Yang","year":"2018","journal-title":"IEEE Access"},{"key":"10.3233\/AIC-230135_ref30","doi-asserted-by":"crossref","unstructured":"X.\u00a0Yang and J.\u00a0Yan, Arbitrary-oriented object detection with circular smooth label, in: European Conference on Computer Vision, Springer, 2020, pp.\u00a0677\u2013694.","DOI":"10.1007\/978-3-030-58598-3_40"},{"issue":"5","key":"10.3233\/AIC-230135_ref31","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1007\/s11263-022-01593-w","article-title":"On the arbitrary-oriented object detection: Classification based approaches revisited","volume":"130","author":"Yang","year":"2022","journal-title":"International Journal of Computer Vision"},{"key":"10.3233\/AIC-230135_ref32","doi-asserted-by":"crossref","unstructured":"X.\u00a0Yang, J.\u00a0Yan, Z.\u00a0Feng and T.\u00a0He, R3det: Refined single-stage detector with feature refinement for rotating object, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol.\u00a035, 2021, pp.\u00a03163\u20133171.","DOI":"10.1609\/aaai.v35i4.16426"},{"key":"10.3233\/AIC-230135_ref33","unstructured":"X.\u00a0Yang, J.\u00a0Yan, Q.\u00a0Ming, W.\u00a0Wang, X.\u00a0Zhang and Q.\u00a0Tian, Rethinking rotated object detection with Gaussian Wasserstein distance loss, in: International Conference on Machine Learning, PMLR, 2021, pp.\u00a011830\u201311841."},{"key":"10.3233\/AIC-230135_ref34","doi-asserted-by":"crossref","unstructured":"X.\u00a0Yang, J.\u00a0Yang, J.\u00a0Yan, Y.\u00a0Zhang, T.\u00a0Zhang, Z.\u00a0Guo, X.\u00a0Sun and K.\u00a0Fu, Scrdet: Towards more robust detection for small, cluttered and rotated objects, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp.\u00a08232\u20138241.","DOI":"10.1109\/ICCV.2019.00832"},{"key":"10.3233\/AIC-230135_ref35","first-page":"18381","article-title":"Learning high-precision bounding box for rotated object detection via Kullback-Leibler divergence","volume":"34","author":"Yang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/AIC-230135_ref37","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Yang, S.\u00a0Liu, H.\u00a0Hu, L.\u00a0Wang and S.\u00a0Lin, Reppoints: Point set representation for object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp.\u00a09657\u20139666.","DOI":"10.1109\/ICCV.2019.00975"}],"container-title":["AI Communications"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/AIC-230135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T18:28:12Z","timestamp":1777400892000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/AIC-230135"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,21]]},"references-count":35,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.3233\/aic-230135","relation":{},"ISSN":["1875-8452","0921-7126"],"issn-type":[{"value":"1875-8452","type":"electronic"},{"value":"0921-7126","type":"print"}],"subject":[],"published":{"date-parts":[[2024,3,21]]}}}