{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T15:46:29Z","timestamp":1782229589609,"version":"3.54.5"},"reference-count":58,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2023,3,20]],"date-time":"2023-03-20T00:00:00Z","timestamp":1679270400000},"content-version":"vor","delay-in-days":170,"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172218"],"award-info":[{"award-number":["62172218"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A1515010170"],"award-info":[{"award-number":["2022A1515010170"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"published-print":{"date-parts":[[2022,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Adverse weather conditions such as haze, rain, and snow often impair the quality of captured images, causing detection networks trained on normal images to generalize poorly in these scenarios. In this paper, we raise an intriguing question \u2013 if the combination of image restoration and object detection, can boost the performance of cutting\u2010edge detectors in adverse weather conditions. To answer it, we propose an effective yet unified detection paradigm that bridges these two subtasks together via dynamic enhancement learning to discern objects in adverse weather conditions, called TogetherNet. Different from existing efforts that intuitively apply image dehazing\/deraining as a pre\u2010processing step, TogetherNet considers a multi\u2010task joint learning problem. Following the joint learning scheme, clean features produced by the restoration network can be shared to learn better object detection in the detection network, thus helping TogetherNet enhance the detection capacity in adverse weather conditions. Besides the joint learning architecture, we design a new Dynamic Transformer Feature Enhancement module to improve the feature extraction and representation capabilities of TogetherNet. Extensive experiments on both synthetic and real\u2010world datasets demonstrate that our TogetherNet outperforms the state\u2010of\u2010the\u2010art detection approaches by a large margin both quantitatively and qualitatively. Source code is available at <jats:ext-link xmlns:xlink=\"https:\/\/2.zoppoz.workers.dev:443\/http\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/2.zoppoz.workers.dev:443\/https\/github.com\/yz-wang\/TogetherNet\">https:\/\/2.zoppoz.workers.dev:443\/https\/github.com\/yz-wang\/TogetherNet<\/jats:ext-link>.<\/jats:p>","DOI":"10.1111\/cgf.14692","type":"journal-article","created":{"date-parts":[[2023,3,20]],"date-time":"2023-03-20T13:46:27Z","timestamp":1679319987000},"page":"465-476","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":65,"title":["TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learning"],"prefix":"10.1111","volume":"41","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-6020-3211","authenticated-orcid":false,"given":"Yongzhen","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics  Nanjing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-6030-0855","authenticated-orcid":false,"given":"Xuefeng","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics  Nanjing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-6612-5063","authenticated-orcid":false,"given":"Kaiwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics  Nanjing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-5272-6706","authenticated-orcid":false,"given":"Lina","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics  Nanjing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-0965-3617","authenticated-orcid":false,"given":"Haoran","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Computing and Decision Sciences Lingnan University  Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-3976-0053","authenticated-orcid":false,"given":"Fu Lee","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Science and Technology Hong Kong Metropolitan University  Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-0429-490X","authenticated-orcid":false,"given":"Mingqiang","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics  Nanjing China"},{"name":"Shenzhen Research Institute Nanjing University of Aeronautics and Astronautics  Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,3,20]]},"reference":[{"key":"e_1_2_7_2_2","doi-asserted-by":"crossref","unstructured":"BozcanI. KayacanE.: Context-dependent anomaly detection for low altitude traffic surveillance. InProceedings of the IEEE International Conference on Robotics and Automation (ICRA)(2021) pp.224\u2013230. 1","DOI":"10.1109\/ICRA48506.2021.9562043"},{"key":"e_1_2_7_3_2","unstructured":"BochkovskiyA. WangC.-Y. LiaoH.-Y. M.: Yolov4: Optimal speed and accuracy of object detection.arXiv preprint arXiv:2004.10934(2020). 2 3"},{"key":"e_1_2_7_4_2","doi-asserted-by":"crossref","unstructured":"ChenY. LiW. SakaridisC. DaiD. Van GoolL.: Domain adaptive faster r-cnn for object detection in the wild. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2018) pp.3339\u20133348. 1 2","DOI":"10.1109\/CVPR.2018.00352"},{"key":"e_1_2_7_5_2","doi-asserted-by":"crossref","unstructured":"ChenC. SeffA. KornhauserA. XiaoJ.: Deepdriving: Learning affordance for direct perception in autonomous driving. InProceedings of the IEEE International Conference on Computer Vision (ICCV)(2015) pp.2722\u20132730. 1","DOI":"10.1109\/ICCV.2015.312"},{"key":"e_1_2_7_6_2","unstructured":"DosovitskiyA. BeyerL. KolesnikovA. WeissenbornD. ZhaiX. UnterthinerT. DehghaniM. MindererM. HeigoldG. GellyS. et al.: An image is worth 16\u00d716 words: Transformers for image recognition at scale.arXiv preprint arXiv:2010.11929(2020). 5"},{"key":"e_1_2_7_7_2","doi-asserted-by":"crossref","unstructured":"DongH. PanJ. XiangL. HuZ. ZhangX. WangF. YangM.-H.: Multi-scale boosted dehazing network with dense feature fusion. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2020) pp.2157\u20132167. 1","DOI":"10.1109\/CVPR42600.2020.00223"},{"key":"e_1_2_7_8_2","doi-asserted-by":"crossref","unstructured":"DaiJ. QiH. XiongY. LiY. ZhangG. HuH. WeiY.: Deformable convolutional networks. InProceedings of the IEEE International Conference on Computer Vision (ICCV)(2017) pp.764\u2013773. 5","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_2_7_9_2","doi-asserted-by":"crossref","unstructured":"DengS. WeiM. WangJ. FengY. LiangL. XieH. WangF. L. WangM.:Detail-recovery image deraining via context aggregation networks. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2020) pp.14548\u201314557. 3","DOI":"10.1109\/CVPR42600.2020.01457"},{"key":"e_1_2_7_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_2_7_11_2","doi-asserted-by":"crossref","unstructured":"GirshickR. DonahueJ. DarrellT. MalikJ.: Rich feature hierarchies for accurate object detection and semantic segmentation. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2014) pp.580\u2013587. 2","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_2_7_12_2","doi-asserted-by":"crossref","unstructured":"GirshickR.: Fast r-cnn. InProceedings of the IEEE International Conference on Computer Vision (ICCV)(2015) pp.1440\u20131448. 2","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_2_7_13_2","first-page":"999","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","author":"Gopalan R.","year":"2011"},{"key":"e_1_2_7_14_2","unstructured":"GeZ. LiuS. WangF. LiZ. SunJ.: Yolox: Exceeding yolo series in 2021.arXiv preprint arXiv:2107.08430(2021). 2 3 7 8 9 10"},{"issue":"8","key":"e_1_2_7_15_2","first-page":"2623","article-title":"Dsnet: Joint semantic learning for object detection in inclement weather conditions","volume":"43","author":"Huang S.-C.","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_7_16_2","first-page":"3323","volume-title":"Proceedings of the IEEE International Conference on Image Processing (ICIP)","author":"Hnewa M.","year":"2021"},{"key":"e_1_2_7_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.168"},{"key":"e_1_2_7_18_2","doi-asserted-by":"crossref","unstructured":"HeL. ZhouQ. LiX. NiuL. ChengG. LiX. LiuW. TongY. MaL. ZhangL.: End-to-end video object detection with spatial-temporal transformers. InProceedings of the 29th ACM International Conference on Multimedia(2021) pp.1507\u20131516. 1","DOI":"10.1145\/3474085.3475285"},{"key":"e_1_2_7_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3048625"},{"key":"e_1_2_7_20_2","unstructured":"JocherG. StokenA. BorovecJ.:Ultralytics\/yolov5: V4.0\u2013nn.silu() activations weights & biases logging pytorch hub integration Jan 2021. URL:https:\/\/2.zoppoz.workers.dev:443\/https\/zenodo.org\/record\/4418161. 2 3"},{"key":"e_1_2_7_21_2","first-page":"21","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Liu W.","year":"2016"},{"key":"e_1_2_7_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2952690"},{"key":"e_1_2_7_23_2","doi-asserted-by":"crossref","unstructured":"LinT.-Y. GoyalP. GirshickR. HeK. Doll\u00e1rP.: Focal loss for dense object detection. InProceedings of the IEEE International Conference on Computer Vision (ICCV)(2017) pp.2980\u20132988. 2 6","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_2_7_24_2","doi-asserted-by":"crossref","unstructured":"LiuJ.-J. HouQ. ChengM.-M. WangC. FengJ.: Improving convolutional networks with self-calibrated convolutions. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2020) pp.10096\u201310105. 3 5","DOI":"10.1109\/CVPR42600.2020.01011"},{"key":"e_1_2_7_25_2","doi-asserted-by":"crossref","unstructured":"LiH. LiJ. ZhaoD. XuL.: Dehazeflow: Multi-scale conditional flow network for single image dehazing. InProceedings of the 29th ACM International Conference on Multimedia(2021) pp.2577\u20132585. 1","DOI":"10.1145\/3474085.3475432"},{"key":"e_1_2_7_26_2","first-page":"740","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Lin T.-Y.","year":"2014"},{"key":"e_1_2_7_27_2","doi-asserted-by":"crossref","unstructured":"LiuX. MaY. ShiZ. ChenJ.: Griddehazenet: Attention-based multi-scale network for image dehazing. InProceedings of the IEEE International Conference on Computer Vision (ICCV)(2019). 1","DOI":"10.1109\/ICCV.2019.00741"},{"key":"e_1_2_7_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01247-4"},{"key":"e_1_2_7_29_2","unstructured":"LiB. PengX. WangZ. XuJ. FengD.: Aod-net: All-in-one dehazing network. InProceedings of the IEEE International Conference on Computer Vision (ICCV)(2017) pp.4770\u20134778. 3 7 10"},{"key":"e_1_2_7_30_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13825"},{"key":"e_1_2_7_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2867951"},{"key":"e_1_2_7_32_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20072"},{"key":"e_1_2_7_33_2","doi-asserted-by":"crossref","unstructured":"PangJ. ChenK. ShiJ. FengH. OuyangW. LinD.: Libra r-cnn: Towards balanced learning for object detection. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2019) pp.821\u2013830. 2","DOI":"10.1109\/CVPR.2019.00091"},{"key":"e_1_2_7_34_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6865"},{"key":"e_1_2_7_35_2","doi-asserted-by":"crossref","unstructured":"RoyChowdhuryA. ChakrabartyP. SinghA. JinS. JiangH. CaoL. Learned-MillerE.: Automatic adaptation of object detectors to new domains using self-training. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2019) pp.780\u2013790. 3","DOI":"10.1109\/CVPR.2019.00087"},{"key":"e_1_2_7_36_2","doi-asserted-by":"crossref","unstructured":"RedmonJ. DivvalaS. GirshickR. FarhadiA.: You only look once: Unified real-time object detection. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2016) pp.779\u2013788. 2 3","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_2_7_37_2","doi-asserted-by":"crossref","unstructured":"RedmonJ. FarhadiA.: Yolo9000: better faster stronger. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2017) pp.7263\u20137271. 2 3","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_2_7_38_2","unstructured":"RedmonJ. FarhadiA.: Yolov3: An incremental improvement.arXiv preprint arXiv:1804.02767(2018). 2 3"},{"key":"e_1_2_7_39_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_7_40_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14162"},{"key":"e_1_2_7_41_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14163"},{"key":"e_1_2_7_42_2","doi-asserted-by":"crossref","unstructured":"RezaeianaranF. ShettyR. AljundiR. ReinoD. O. ZhangS. SchieleB.: Seeking similarities over differences: Similarity-based domain alignment for adaptive object detection. InProceedings of the IEEE International Conference on Computer Vision (ICCV)(2021) pp.9204\u20139213. 2","DOI":"10.1109\/ICCV48922.2021.00907"},{"key":"e_1_2_7_43_2","unstructured":"SunT. ChenJ. NgF.: Multi-target domain adaptation via unsupervised domain classification for weather invariant object detection.arXiv preprint arXiv:2103.13970(2021). 1"},{"key":"e_1_2_7_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1072-8"},{"key":"e_1_2_7_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.08.022"},{"key":"e_1_2_7_46_2","first-page":"763","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Sindagi V. A.","year":"2020"},{"key":"e_1_2_7_47_2","doi-asserted-by":"crossref","unstructured":"SaitoK. UshikuY. HaradaT. SaenkoK.: Strong-weak distribution alignment for adaptive object detection. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2019) pp.6956\u20136965. 2","DOI":"10.1109\/CVPR.2019.00712"},{"issue":"2","key":"e_1_2_7_48_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3478457","article-title":"Sadnet: Semi-supervised single image dehazing method based on an attention mechanism","volume":"18","author":"Sun Z.","year":"2022","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"key":"e_1_2_7_49_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"e_1_2_7_50_2","doi-asserted-by":"crossref","unstructured":"WangC.-Y. LiaoH.-Y. M. WuY.-H. ChenP.-Y. HsiehJ.-W. YehI.-H.: Cspnet: A new backbone that can enhance learning capability of cnn. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)(2020) pp.390\u2013391. 3 4","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"e_1_2_7_51_2","first-page":"1","article-title":"Detecting occluded and dense trees in urban terrestrial views with a high-quality tree detection dataset","volume":"60","author":"Wang Y.","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_2_7_52_2","unstructured":"WangY. YanX. GuanD. WeiM. ChenY. ZhangX.-P. LiJ.: Cycle-snspgan: Towards real-world image dehazing via cycle spectral normalized soft likelihood estimation patch gan.IEEE Transactions on Intelligent Transportation Systems(2022) 1\u201315. 3"},{"key":"e_1_2_7_53_2","doi-asserted-by":"crossref","unstructured":"YasarlaR. SindagiV. A. PatelV. M.: Syn2real transfer learning for image deraining using gaussian processes. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2020) pp.2726\u20132736. 9","DOI":"10.1109\/CVPR42600.2020.00280"},{"key":"e_1_2_7_54_2","first-page":"260","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Zhang H.","year":"2020"},{"key":"e_1_2_7_55_2","doi-asserted-by":"crossref","unstructured":"ZhuX. PangJ. YangC. ShiJ. LinD.: Adapting object detectors via selective cross-domain alignment. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2019) pp.687\u2013696. 3","DOI":"10.1109\/CVPR.2019.00078"},{"key":"e_1_2_7_56_2","unstructured":"ZhuX. SuW. LuL. LiB. WangX. DaiJ.: Deformable detr: Deformable transformers for end-to-end object detection.arXiv preprint arXiv:2010.04159(2020). 5"},{"key":"e_1_2_7_57_2","first-page":"785","volume-title":"Asian Conference on Machine Learning","author":"Zhang S.","year":"2021"},{"key":"e_1_2_7_58_2","unstructured":"ZhouX. WangD. Kr\u00e4henb\u00fchlP.: Objects as points.arXiv preprint arXiv:1904.07850(2019). 2"},{"key":"e_1_2_7_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.14692","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.14692","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.14692","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,20]],"date-time":"2023-08-20T22:30:58Z","timestamp":1692570658000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.14692"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":58,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["10.1111\/cgf.14692"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1111\/cgf.14692","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]},"assertion":[{"value":"2023-03-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}