{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T12:25:17Z","timestamp":1772022317312,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2025,4,1]]},"DOI":"10.1587\/transinf.2024edp7204","type":"journal-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T22:13:06Z","timestamp":1730758386000},"page":"371-383","source":"Crossref","is-referenced-by-count":2,"title":["Learn Discriminative Features for Small Object Detection through Multi-Scale Image Degradation with Contrastive Learning"],"prefix":"10.1587","volume":"E108.D","author":[{"given":"Xiaoguang","family":"TU","sequence":"first","affiliation":[{"name":"Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China"},{"name":"School of Computer Science, Sichuan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"HE","sequence":"additional","affiliation":[{"name":"Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gui","family":"FU","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Southwest University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"LIU","sequence":"additional","affiliation":[{"name":"Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mian","family":"ZHONG","sequence":"additional","affiliation":[{"name":"Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"ZHOU","sequence":"additional","affiliation":[{"name":"Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xia","family":"LEI","sequence":"additional","affiliation":[{"name":"Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juhang","family":"YIN","sequence":"additional","affiliation":[{"name":"Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"HUANG","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Southwest University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"WANG","sequence":"additional","affiliation":[{"name":"Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] X. Huang and L. Du, \u201cFire detection and recognition optimization based on virtual reality video image,\u201d IEEE Access, vol.8, pp.77951-77961, 2020. 10.1109\/access.2020.2990224","DOI":"10.1109\/ACCESS.2020.2990224"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] J. Wang, W. Yang, H. Guo, R. Zhang, and G.-S. Xia, \u201cTiny object detection in aerial images,\u201d 2020 25th international conference on pattern recognition (ICPR), pp.3791-3798, IEEE, 2021. 10.1109\/icpr48806.2021.9413340","DOI":"10.1109\/ICPR48806.2021.9413340"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] Y. Cai, T. Luan, H. Gao, H. Wang, L. Chen, Y. Li, M.A. Sotelo, and Z. Li, \u201cYolov4-5d: An effective and efficient object detector for autonomous driving,\u201d IEEE Trans. Instrum. Meas., vol.70, pp.1-13, 2021. 10.1109\/tim.2021.3065438","DOI":"10.1109\/TIM.2021.3065438"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] S. Sambolek and M. Ivasic-Kos, \u201cAutomatic person detection in search and rescue operations using deep cnn detectors,\u201d IEEE Access, vol.9, pp.37905-37922, 2021. 10.1109\/access.2021.3063681","DOI":"10.1109\/ACCESS.2021.3063681"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] S. Zhai, D. Shang, S. Wang, and S. Dong, \u201cDf-ssd: An improved ssd object detection algorithm based on densenet and feature fusion,\u201d IEEE access, vol.8, pp.24344-24357, 2020. 10.1109\/access.2020.2971026","DOI":"10.1109\/ACCESS.2020.2971026"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] Q.-C. Mao, H.-M. Sun, Y.-B. Liu, and R.-S. Jia, \u201cMini-yolov3: real-time object detector for embedded applications,\u201d IEEE Access, vol.7, pp.133529-133538, 2019. 10.1109\/access.2019.2941547","DOI":"10.1109\/ACCESS.2019.2941547"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] X. Zhu, S. Lyu, X. Wang, and Q. Zhao, \u201cTph-yolov5: Improved yolov5 based on transformer prediction head for object detection on drone-captured scenarios,\u201d Proc. IEEE\/CVF international conference on computer vision, pp.2778-2788, 2021. 10.1109\/iccvw54120.2021.00312","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] R. Girshick, \u201cFast r-cnn,\u201d Proc. IEEE international conference on computer vision, pp.1440-1448, 2015. 10.1109\/iccv.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] K. He, G. Gkioxari, P. Doll\u00e1r, and R. Girshick, \u201cMask r-cnn,\u201d Proc. IEEE international conference on computer vision, pp.2961-2969, 2017. 10.1109\/iccv.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"10","doi-asserted-by":"publisher","unstructured":"[10] Y. Zhang and M. Chi, \u201cMask-r-fcn: A deep fusion network for semantic segmentation,\u201d IEEE Access, vol.8, pp.155753-155765, 2020. 10.1109\/access.2020.3012701","DOI":"10.1109\/ACCESS.2020.3012701"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] A. Betti and M. Tucci, \u201cYolo-s: A lightweight and accurate yolo-like network for small target detection in aerial imagery,\u201d Sensors, vol.23, no.4, p.1865, 2023. 10.3390\/s23041865","DOI":"10.3390\/s23041865"},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] Z. Wei, D. Liang, D. Zhang, L. Zhang, Q. Geng, M. Wei, and H. Zhou, \u201cLearning calibrated-guidance for object detection in aerial images,\u201d IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol.15, pp.2721-2733, 2022. 10.1109\/jstars.2022.3158903","DOI":"10.1109\/JSTARS.2022.3158903"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] Y. Gong, X. Yu, Y. Ding, X. Peng, J. Zhao, and Z. Han, \u201cEffective fusion factor in fpn for tiny object detection,\u201d Proc. IEEE\/CVF winter conference on applications of computer vision, pp.1160-1168, 2021. 10.1109\/wacv48630.2021.00120","DOI":"10.1109\/WACV48630.2021.00120"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] X. Zhu, B. Liang, D. Fu, G. Huang, F. Yang, and W. Li, \u201cAirport small object detection based on feature enhancement,\u201d IET Image Processing, vol.16, no.11, pp.2863-2874, 2022. 10.1049\/ipr2.12387","DOI":"10.1049\/ipr2.12387"},{"key":"15","doi-asserted-by":"publisher","unstructured":"[15] K. Li, Y. Wang, and Z. Hu, \u201cImproved yolov7 for small object detection algorithm based on attention and dynamic convolution,\u201d Applied Sciences, vol.13, no.16, p.9316, 2023. 10.3390\/app13169316","DOI":"10.3390\/app13169316"},{"key":"16","doi-asserted-by":"publisher","unstructured":"[16] J. Zhang, G. Wan, M. Jiang, G. Lu, X. Tao, and Z. Huang, \u201cSmall object detection in uav image based on improved yolov5,\u201d Systems Science & Control Engineering, vol.11, no.1, p.2247082, 2023. 10.1080\/21642583.2023.2247082","DOI":"10.1080\/21642583.2023.2247082"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] J. Seo, W. Bae, D.J. Sutherland, J. Noh, and D. Kim, \u201cObject discovery via contrastive learning for weakly supervised object detection,\u201d European conference on computer vision, pp.312-329, Springer, 2022. 10.1007\/978-3-031-19821-2_18","DOI":"10.1007\/978-3-031-19821-2_18"},{"key":"18","doi-asserted-by":"publisher","unstructured":"[18] D. Biswas and J. Te\u0161i\u0107, \u201cDomain adaptation with contrastive learning for object detection in satellite imagery,\u201d IEEE Trans. Geosci. Remote Sens., vol.62, pp.1-15, 2024. 10.1109\/tgrs.2024.3391621","DOI":"10.1109\/TGRS.2024.3391621"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] K. He, H. Fan, Y. Wu, S. Xie, and R. Girshick, \u201cMomentum contrast for unsupervised visual representation learning,\u201d Proc. IEEE\/CVF conference on computer vision and pattern recognition, pp.9729-9738, 2020. 10.1109\/cvpr42600.2020.00975","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] T.-Y. Lin, P. Doll\u00e1r, R. Girshick, K. He, B. Hariharan, and S. Belongie, \u201cFeature pyramid networks for object detection,\u201d Proc. IEEE conference on computer vision and pattern recognition, pp.2117-2125, 2017. 10.1109\/cvpr.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"21","unstructured":"[21] H. Li, P. Xiong, J. An, and L. Wang, \u201cPyramid attention network for semantic segmentation,\u201d arXiv preprint arXiv:1805.10180, 2018."},{"key":"22","doi-asserted-by":"publisher","unstructured":"[22] Z. Zheng, P. Wang, W. Liu, J. Li, R. Ye, and D. Ren, \u201cDistance-iou loss: Faster and better learning for bounding box regression,\u201d Proc. AAAI conference on artificial intelligence, vol.34, no.7, pp.12993-13000, 2020. 10.1609\/aaai.v34i07.6999","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Doll\u00e1r, and C.L. Zitnick, \u201cMicrosoft coco: Common objects in context,\u201d Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp.740-755, Springer, 2014. 10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"24","unstructured":"[24] D. Du, P. Zhu, L. Wen, X. Bian, H. Lin, Q. Hu, T. Peng, J. Zheng, X. Wang, Y. Zhang, L. Bo, H. Shi, R. Zhu, B. Dong, D.R. Pailla, F. Ni, G. Gao, G. Liu, H. Xiong, J. Ge, J. Zhou, J. Hu, L. Sun, L. Chen, M. Lauer, Q. Liu, S.S. Chennamsetty, T. Sun, T. Wu, V.A. Kollerathu, W. Tian, W. Qin, X. Chen, X. Zhao, Y. Lian, Y. Wu, Y. Li, Y. Li, Y. Wang, Y. Song, Y. Yao, Y. Zhang, Z. Pi, Z. Chen, Z. Xu, Z. Xiao, Z. Luo, and Z. Liu, \u201cVisdrone-det2019: The vision meets drone object detection in image challenge results,\u201d Proc. IEEE\/CVF international conference on computer vision workshops, pp.227-235, 2019. 10.1109\/iccvw.2019.00031"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] X. Li, W. Wang, X. Hu, J. Li, J. Tang, and J. Yang, \u201cGeneralized focal loss v2: Learning reliable localization quality estimation for dense object detection,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.11632-11641, 2021. 10.1109\/cvpr46437.2021.01146","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] X. Dai, Y. Chen, B. Xiao, D. Chen, M. Liu, L. Yuan, and L. Zhang, \u201cDynamic head: Unifying object detection heads with attentions,\u201d Proc. IEEE\/CVF conference on computer vision and pattern recognition, pp.7373-7382, 2021. 10.1109\/cvpr46437.2021.00729","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] Z. Sun, S. Cao, Y. Yang, and K.M. Kitani, \u201cRethinking transformer-based set prediction for object detection,\u201d Proc. IEEE\/CVF international conference on computer vision, pp.3611-3620, 2021. 10.1109\/iccv48922.2021.00359","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] D. Meng, X. Chen, Z. Fan, G. Zeng, H. Li, Y. Yuan, L. Sun, and J. Wang, \u201cConditional detr for fast training convergence,\u201d Proc. IEEE\/CVF International Conference on Computer Vision, pp.3651-3660, 2021. 10.1109\/iccv48922.2021.00363","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"29","unstructured":"[29] Z. Yao, J. Ai, B. Li, and C. Zhang, \u201cEfficient detr: improving end-to-end object detector with dense prior,\u201d arXiv preprint arXiv:2104.01318, 2021."},{"key":"30","unstructured":"[30] X. Long, K. Deng, G. Wang, Y. Zhang, Q. Dang, Y. Gao, H. Shen, J. Ren, S. Han, E. Ding, and S. Wen, \u201cPp-yolo: An effective and efficient implementation of object detector,\u201d arXiv preprint arXiv:2007.12099, 2020."},{"key":"31","unstructured":"[31] C. Picron and T. Tuytelaars, \u201cEffseg: Efficient fine-grained instance segmentation using structure-preserving sparsity,\u201d arXiv preprint arXiv:2307.01545, 2023."},{"key":"32","unstructured":"[32] X. Zhu, W. Su, L. Lu, B. Li, X. Wang, and J. Dai, \u201cDeformable detr: Deformable transformers for end-to-end object detection,\u201d arXiv preprint arXiv:2010.04159, 2020."},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] Z. Gao, L. Wang, B. Han, and S. Guo, \u201cAdamixer: A fast-converging query-based object detector,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.5364-5373, 2022. 10.1109\/cvpr52688.2022.00529","DOI":"10.1109\/CVPR52688.2022.00529"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] C.-Y. Wang, A. Bochkovskiy, and H.-Y.M. Liao, \u201cScaled-yolov4: Scaling cross stage partial network,\u201d Proc. IEEE\/cvf conference on computer vision and pattern recognition, pp.13029-13038, 2021. 10.1109\/cvpr46437.2021.01283","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"35","unstructured":"[35] X. Huang, X. Wang, W. Lv, X. Bai, X. Long, K. Deng, Q. Dang, S. Han, Q. Liu, X. Hu, D. Yu, Y. Ma, and O. Yoshie \u201cPp-yolov2: A practical object detector,\u201d arXiv preprint arXiv:2104.10419, 2021."},{"key":"36","doi-asserted-by":"crossref","unstructured":"[36] F. Li, H. Zhang, S. Liu, J. Guo, L.M. Ni, and L. Zhang, \u201cDn-detr: Accelerate detr training by introducing query denoising,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.13619-13627, 2022. 10.1109\/cvpr52688.2022.01325","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"37","doi-asserted-by":"crossref","unstructured":"[37] M. Tan, R. Pang, and Q.V. Le, \u201cEfficientdet: Scalable and efficient object detection,\u201d Proc. IEEE\/CVF conference on computer vision and pattern recognition, pp.10781-10790, 2020. 10.1109\/cvpr42600.2020.01079","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"38","unstructured":"[38] C. Li, L. Li, H. Jiang, K. Weng, Y. Geng, L. Li, Z. Ke, Q. Li, M. Cheng, W. Nie, Y. Li, B. Zhang, Y. Liang, L. Zhou, X. Xu, X. Chu, X. Wei, and X. Wei, \u201cYolov6: A single-stage object detection framework for industrial applications,\u201d arXiv preprint arXiv:2209.02976, 2022."},{"key":"39","doi-asserted-by":"crossref","unstructured":"[39] C.-Y. Wang, A. Bochkovskiy, and H.-Y.M. Liao, \u201cYolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.7464-7475, 2023. 10.1109\/cvpr52729.2023.00721","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"40","doi-asserted-by":"crossref","unstructured":"[40] H. Liu, F. Sun, J. Gu, and L. Deng, \u201cSf-yolov5: A lightweight small object detection algorithm based on improved feature fusion mode,\u201d Sensors, vol.22, no.15, p.5817, 2022. 10.3390\/s22155817","DOI":"10.3390\/s22155817"},{"key":"41","unstructured":"[41] A. Bochkovskiy, C.Y. Wang, and H.Y.M. Liao, \u201cYolov4: Optimal speed and accuracy of object detection,\u201d arXiv preprint arXiv:2004.10934, 2020."},{"key":"42","doi-asserted-by":"publisher","unstructured":"[42] H. Liu, X. Duan, H. Lou, J. Gu, H. Chen, and L. Bi, \u201cImproved gbs-yolov5 algorithm based on yolov5 applied to uav intelligent traffic,\u201d Scientific Reports, vol.13, no.1, p.9577, 2023. 10.1038\/s41598-023-36781-2","DOI":"10.1038\/s41598-023-36781-2"},{"key":"43","doi-asserted-by":"publisher","unstructured":"[43] J. Shang, J. Wang, S. Liu, C. Wang, and B. Zheng, \u201cSmall target detection algorithm for uav aerial photography based on improved yolov5s,\u201d Electronics, vol.12, no.11, p.2434, 2023. 10.3390\/electronics12112434","DOI":"10.3390\/electronics12112434"},{"key":"44","unstructured":"[44] G. Jocher, A. Stoken, J. Borovec, A. Chaurasia, L. Changyu, A. Hogan, J. Hajek, L. Diaconu, Y. Kwon, Y. Defretin, et al., \u201cultralytics\/yolov5: v5.0-yolov5-p6 1280 models, aws, supervisely and Youtube integrations,\u201d Zenodo, 2021."},{"key":"45","doi-asserted-by":"crossref","unstructured":"[45] K. Ding, X. Li, W. Guo, and L. Wu, \u201cImproved object detection algorithm for drone-captured dataset based on yolov5,\u201d 2022 2nd International Conference on Consumer Electronics and Computer Engineering (ICCECE), pp.895-899, IEEE, 2022. 10.1109\/iccece54139.2022.9712813","DOI":"10.1109\/ICCECE54139.2022.9712813"},{"key":"46","unstructured":"[46] S. Xu, X. Wang, W. Lv, Q. Chang, C. Cui, K. Deng, G. Wang, Q. Dang, S. Wei, Y. Du, and B. Lai, \u201cPp-yoloe: An evolved version of yolo,\u201d arXiv preprint arXiv:2203.16250, 2022."}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/4\/E108.D_2024EDP7204\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T03:26:05Z","timestamp":1743823565000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/4\/E108.D_2024EDP7204\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,1]]},"references-count":46,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2024edp7204","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,1]]},"article-number":"2024EDP7204"}}