{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T10:22:51Z","timestamp":1772360571804,"version":"3.50.1"},"reference-count":68,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T00:00:00Z","timestamp":1681430400000},"content-version":"vor","delay-in-days":103,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1805400"],"award-info":[{"award-number":["2020YFB1805400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42071431"],"award-info":[{"award-number":["42071431"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p>Object detection remains challenging in hazy weather conditions due to the poor visibility of captured images. There are currently two types of detectors capable of adapting to varying weather conditions: (i) low\u2010level adaptation methods that combine one detector with an additional dehazing network and (ii) high\u2010level adaptation methods that explore various kinds of domain adaptation knowledge. However, neither of these approaches can achieve desirable performance due to their inherent limitations. We raise an intriguing question\u2014if combining both low\u2010level adaptation and high\u2010level adaptation, can improve the generalization ability of a detector in hazy weather conditions? To answer it, we propose a Joint High\u2010Low Adaptation Object Detection paradigm (HLA\u2010HOD) in hazy weather conditions. By combining both low\u2010level adaptation and high\u2010level adaptation, HLA\u2010HOD achieves superior performance on hazy images without requiring ground\u2010truth bounding boxes or clean images. Extensive experiments demonstrate that our method outperforms state\u2010of\u2010the\u2010art low\u2010level and high\u2010level adaptation methods by a large margin both quantitatively and qualitatively.<\/jats:p>","DOI":"10.1155\/2023\/3691730","type":"journal-article","created":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T19:35:08Z","timestamp":1681500908000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["HLA\u2010HOD: Joint High\u2010Low Adaptation for Object Detection in Hazy Weather Conditions"],"prefix":"10.1155","volume":"2023","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2311-0950","authenticated-orcid":false,"given":"Yiyang","family":"Shen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1376-2720","authenticated-orcid":false,"given":"Rongwei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8635-9863","authenticated-orcid":false,"given":"Ni","family":"Shu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7059-0929","authenticated-orcid":false,"given":"Jing","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0429-490X","authenticated-orcid":false,"given":"Mingqiang","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2023,4,14]]},"reference":[{"key":"e_1_2_8_1_2","doi-asserted-by":"crossref","unstructured":"BozcanI.andKayacanE. Context-dependent anomaly detection for low altitude traffic surveillance Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA) June 2021 Xi\u2032an China 224\u2013230.","DOI":"10.1109\/ICRA48506.2021.9562043"},{"key":"e_1_2_8_2_2","doi-asserted-by":"crossref","unstructured":"ChenC. SeffA. KornhauserA. andXiaoJ. Deepdriving: learning affordance for direct perception in autonomous driving Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV) December 2015 Santiago Chile 2722\u20132730.","DOI":"10.1109\/ICCV.2015.312"},{"key":"e_1_2_8_3_2","doi-asserted-by":"crossref","unstructured":"RedmonJ. DivvalaS. GirshickR. andFarhadiA. You only look once: unified real-time object detection 2016 779\u2013788 https:\/\/arxiv.org\/abs\/1506.02640.","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_2_8_4_2","unstructured":"RedmonJ.andFarhadiA. YOLO9000: better faster stronger 2017 7263\u20137271 https:\/\/arxiv.org\/abs\/1612.08242."},{"key":"e_1_2_8_5_2","unstructured":"GeZ. LiuS. WangF. LiZ. andSunJ. Yolox: Exceeding yolo Series in 2021 2021 https:\/\/arxiv.org\/abs\/2107.08430."},{"key":"e_1_2_8_6_2","doi-asserted-by":"publisher","DOI":"10.1002\/int.22513"},{"key":"e_1_2_8_7_2","doi-asserted-by":"publisher","DOI":"10.1002\/int.22646"},{"key":"e_1_2_8_8_2","doi-asserted-by":"crossref","unstructured":"GirshickR. DonahueJ. DarrellT. andMalikJ. Rich feature hierarchies for accurate object detection and semantic segmentation 2014 580\u2013587 https:\/\/arxiv.org\/abs\/1311.2524.","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_2_8_9_2","doi-asserted-by":"crossref","unstructured":"GirshickR. Fast r-cnn Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV) December 2015 Santiago Chile 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_2_8_10_2","article-title":"Faster r-cnn: towards real-time object detection with region proposal networks","volume":"28","author":"Ren S.","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_11_2","doi-asserted-by":"crossref","unstructured":"LiuW. AnguelovD. andErhanD. Ssd: single shot multibox detector 2016 21\u201337 https:\/\/arxiv.org\/abs\/1512.02325.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_2_8_12_2","unstructured":"WangW. YangW. andLiuJ. Hla-face: joint high-low adaptation for low light face detection 2021 16195\u201316204 https:\/\/arxiv.org\/abs\/2104.01984."},{"key":"e_1_2_8_13_2","doi-asserted-by":"crossref","unstructured":"ShenZ. LiuZ. LiJ. JiangY. G. ChenY. andXueX. Dsod: learning deeply supervised object detectors from scratch 2017 1919\u20131927 https:\/\/arxiv.org\/abs\/1708.01241.","DOI":"10.1109\/ICCV.2017.212"},{"key":"e_1_2_8_14_2","unstructured":"FuC. Y. LiuW. RangaA. TyagiA. andBergA. C. Dssd: deconvolutional single shot detector 2017 https:\/\/arxiv.org\/abs\/1701.06659."},{"key":"e_1_2_8_15_2","unstructured":"LinT. Y. GoyalP. GirshickR. HeK. andDoll\u00e1rP. Focal loss for dense object detection 2017 2980\u20132988 https:\/\/arxiv.org\/abs\/1708.02002."},{"key":"e_1_2_8_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.168"},{"key":"e_1_2_8_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2015.2446191"},{"key":"e_1_2_8_18_2","doi-asserted-by":"crossref","unstructured":"TanR. T. Visibility in bad weather from a single image Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition June 2008 Anchorage AK USA 1\u20138.","DOI":"10.1109\/CVPR.2008.4587643"},{"key":"e_1_2_8_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2016.2598681"},{"key":"e_1_2_8_20_2","doi-asserted-by":"crossref","unstructured":"RenW. LiuS. ZhangH. PanJ. CaoX. andYangM. H. Single image dehazing via multi-scale convolutional neural networks Proceedings of the Computer Vision--ECCV 2016: 14th European Conference October 2016 Amsterdam The Netherlands 154\u2013169.","DOI":"10.1007\/978-3-319-46475-6_10"},{"key":"e_1_2_8_21_2","doi-asserted-by":"crossref","unstructured":"LiB. PengX. WangZ. XuJ. andFengD. Aod-net: all-in-one dehazing network Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV) October 2017 Venice Italy 4770\u20134778.","DOI":"10.1109\/ICCV.2017.511"},{"key":"e_1_2_8_22_2","doi-asserted-by":"publisher","DOI":"10.1002\/int.22627"},{"key":"e_1_2_8_23_2","doi-asserted-by":"crossref","unstructured":"EnginD. Gen\u00e7A. andKemal EkenelH. Cycle-dehaze: enhanced cyclegan for single image dehazing Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) June 2018 Salt Lake City UT USA 825\u2013833.","DOI":"10.1109\/CVPRW.2018.00127"},{"key":"e_1_2_8_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2020.3007844"},{"key":"e_1_2_8_25_2","doi-asserted-by":"crossref","unstructured":"YangY. WangC. LiuR. ZhangL. GuoX. andTaoD. Self-augmented unpaired image dehazing via density and depth decomposition Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2022 New Orleans LA USA 2037\u20132046.","DOI":"10.1109\/CVPR52688.2022.00208"},{"key":"e_1_2_8_26_2","unstructured":"ValanarasuJ. M. J. YasarlaR. andPatelV. M. Transweather: Transformer-based restoration of images degraded by adverse weather conditions 2022 2353\u20132363 https:\/\/arxiv.org\/abs\/2111.14813."},{"key":"e_1_2_8_27_2","unstructured":"SongY. HeZ. QianH. andDuX. Vision transformers for single image dehazing 2022 https:\/\/arxiv.org\/abs\/2204.03883."},{"key":"e_1_2_8_28_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20072"},{"key":"e_1_2_8_29_2","doi-asserted-by":"crossref","unstructured":"LeeY. JeonJ. KoY. JeonB. andJeonM. Task-driven deep image enhancement network for autonomous driving in bad weather 2021 13746\u201313753 https:\/\/arxiv.org\/abs\/2110.07206.","DOI":"10.1109\/ICRA48506.2021.9561076"},{"key":"e_1_2_8_30_2","doi-asserted-by":"crossref","unstructured":"DongH. PanJ. andXiangL. Multi-scale boosted dehazing network with dense feature fusion Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2020 Seattle WA USA 2157\u20132167.","DOI":"10.1109\/CVPR42600.2020.00223"},{"key":"e_1_2_8_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.2977911"},{"key":"e_1_2_8_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3125679"},{"key":"e_1_2_8_33_2","doi-asserted-by":"crossref","unstructured":"HnewaM.andRadhaH. Multiscale domain adaptive yolo for cross-domain object detection 2021 3323\u20133327 https:\/\/arxiv.org\/abs\/2106.01483.","DOI":"10.1109\/ICIP42928.2021.9506039"},{"key":"e_1_2_8_34_2","unstructured":"RezaeianaranF. ShettyR. AljundiR. ReinoD. O. ZhangS. andSchieleB. Seeking similarities over differences: similarity-based domain alignment for adaptive object detection 2021 9204\u20139213 https:\/\/arxiv.org\/abs\/2110.01428."},{"key":"e_1_2_8_35_2","doi-asserted-by":"crossref","unstructured":"ChenY. LiW. SakaridisC. DaiD. andVan GoolL. Domain adaptive faster r-cnn for object detection in the wild 2018 3339\u20133348 https:\/\/arxiv.org\/abs\/1803.03243.","DOI":"10.1109\/CVPR.2018.00352"},{"key":"e_1_2_8_36_2","unstructured":"XuM. WangH. NiB. TianQ. andZhangW. Cross-domain detection via graph-induced prototype alignment 2020 12355\u201312364 https:\/\/arxiv.org\/abs\/2003.12849."},{"key":"e_1_2_8_37_2","unstructured":"HeZ.andZhangL. Multi-adversarialfaster-rcnn for unrestricted object detection 2019 6668\u20136677 https:\/\/arxiv.org\/abs\/1907.10343."},{"key":"e_1_2_8_38_2","unstructured":"SaitoK. UshikuY. HaradaT. andSaenkoK. Strong-weak distribution alignment for adaptive object detection 2019 6956\u20136965 https:\/\/arxiv.org\/abs\/1812.04798."},{"key":"e_1_2_8_39_2","article-title":"Deepexposure: learning to expose photos with asynchronously reinforced adversarial learning","volume":"31","author":"Yu R.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_40_2","doi-asserted-by":"crossref","unstructured":"InoueN. FurutaR. YamasakiT. andAizawaK. Cross-domainweakly-supervised object detection through progressive domain adaptation 2018 5001\u20135009 https:\/\/arxiv.org\/abs\/1803.11365.","DOI":"10.1109\/CVPR.2018.00525"},{"key":"e_1_2_8_41_2","doi-asserted-by":"crossref","unstructured":"KhodabandehM. VahdatA. RanjbarM. andMacreadyW. G. A robust learning approach to domain adaptive object detection 2019 480\u2013490 https:\/\/arxiv.org\/abs\/1904.02361.","DOI":"10.1109\/ICCV.2019.00057"},{"key":"e_1_2_8_42_2","doi-asserted-by":"crossref","unstructured":"NarasimhanS. G.andNayarS. K. Chromatic framework for vision in bad weather Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662) June 2000 Hilton Head SC USA 598\u2013605.","DOI":"10.1109\/CVPR.2000.855874"},{"key":"e_1_2_8_43_2","doi-asserted-by":"publisher","DOI":"10.1023\/a:1016328200723"},{"key":"e_1_2_8_44_2","unstructured":"ZhuJ. Y. ParkT. IsolaP. andEfrosA. A. Unpaired image-to-image translation using cycle-consistent adversarial networks 2017 2223\u20132232 https:\/\/arxiv.org\/abs\/1703.10593."},{"key":"e_1_2_8_45_2","unstructured":"LinG. MilanA. ShenC. andReidI. Refinenet: multi-path refinement networks for high-resolution semantic segmentation 2017 1925\u20131934 https:\/\/arxiv.org\/abs\/1611.06612."},{"key":"e_1_2_8_46_2","unstructured":"HeK. ZhangX. RenS. andSunJ. Deep residual learning for image recognition 2016 770\u2013778 https:\/\/arxiv.org\/abs\/1512.03385."},{"key":"e_1_2_8_47_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_48_2","unstructured":"MaoX. LiQ. XieH. LauR. Y. WangZ. andPaul SmolleyS. Least squares generative adversarial networks 2017 2794\u20132802 https:\/\/arxiv.org\/abs\/1611.04076."},{"key":"e_1_2_8_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2022.3170328"},{"key":"e_1_2_8_50_2","unstructured":"CarlucciF. M. D\u2019InnocenteA. BucciS. CaputoB. andTommasiT. Domain generalization by solving jigsaw puzzles 2019 2229\u20132238 https:\/\/arxiv.org\/abs\/1903.06864."},{"key":"e_1_2_8_51_2","unstructured":"HeK. FanH. WuY. XieS. andGirshickR. Momentum contrast for unsupervised visual representation learning 2020 9729\u20139738 https:\/\/arxiv.org\/abs\/1911.05722."},{"key":"e_1_2_8_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2019.2952690"},{"key":"e_1_2_8_53_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6865"},{"key":"e_1_2_8_54_2","unstructured":"WuH. QuY. andLinS. Contrastive learning for compact single image dehazing 2021 10551\u201310560 https:\/\/arxiv.org\/abs\/2104.09367."},{"key":"e_1_2_8_55_2","doi-asserted-by":"crossref","unstructured":"D\u2019InnocenteA. BorlinoF. C. BucciS. CaputoB. andTommasiT. One-shot unsupervised cross-domain detection 2020 732\u2013748 https:\/\/arxiv.org\/abs\/2005.11610.","DOI":"10.1007\/978-3-030-58517-4_43"},{"key":"e_1_2_8_56_2","unstructured":"DengJ. LiW. ChenY. andDuanL. Unbiased mean teacher for cross-domain object detection 2021 4091\u20134101 https:\/\/arxiv.org\/abs\/2003.00707."},{"key":"e_1_2_8_57_2","doi-asserted-by":"crossref","unstructured":"LiC. DuD. andZhangL. Spatial attention pyramid network for unsupervised domain adaptation 2020 481\u2013497 https:\/\/arxiv.org\/abs\/2003.12979.","DOI":"10.1007\/978-3-030-58601-0_29"},{"key":"e_1_2_8_58_2","doi-asserted-by":"crossref","unstructured":"HsuC. C. TsaiY. H. LinY. Y. andYangM. H. Every pixel matters: center-aware feature alignment for domain adaptive object detector 2020 733\u2013748 https:\/\/arxiv.org\/abs\/2008.08574.","DOI":"10.1007\/978-3-030-58545-7_42"},{"key":"e_1_2_8_59_2","doi-asserted-by":"crossref","unstructured":"TianZ. ShenC. ChenH. andHeT. Fcos: fully convolutional one-stage object detection 2019 9627\u20139636 https:\/\/arxiv.org\/abs\/1904.01355.","DOI":"10.1109\/ICCV.2019.00972"},{"key":"e_1_2_8_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1072-8"},{"key":"e_1_2_8_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2018.2867951"},{"key":"e_1_2_8_62_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_2_8_63_2","doi-asserted-by":"crossref","unstructured":"SindagiV. A. OzaP. YasarlaR. andPatelV. M. Prior-based domain adaptive object detection for hazy and rainy conditions 2020 763\u2013780 https:\/\/arxiv.org\/abs\/1912.00070.","DOI":"10.1007\/978-3-030-58568-6_45"},{"key":"e_1_2_8_64_2","doi-asserted-by":"crossref","unstructured":"CordtsM. OmranM. andRamosS. The cityscapes dataset for semantic urban scene understanding 2016 3213\u20133223 https:\/\/arxiv.org\/abs\/1604.01685.","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_2_8_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2019.2952032"},{"key":"e_1_2_8_66_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01431-5"},{"key":"e_1_2_8_67_2","doi-asserted-by":"crossref","unstructured":"ChenZ. WangY. YangY. andLiuD. PSD: principled synthetic-to-real dehazing guided by physical priors Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2021 Nashville TN USA 7180\u20137189.","DOI":"10.1109\/CVPR46437.2021.00710"},{"key":"e_1_2_8_68_2","unstructured":"KomodakisN.andGidarisS. Unsupervised representation learning by predicting image rotations 2018 https:\/\/arxiv.org\/abs\/1803.07728."}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2023\/3691730.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2023\/3691730.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2023\/3691730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T05:12:57Z","timestamp":1735621977000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2023\/3691730"}},"subtitle":[],"editor":[{"given":"Vasudevan","family":"Rajamohan","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":68,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1155\/2023\/3691730"],"URL":"https:\/\/doi.org\/10.1155\/2023\/3691730","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]},"assertion":[{"value":"2022-12-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-03-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-04-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3691730"}}