{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:23:53Z","timestamp":1773156233746,"version":"3.50.1"},"reference-count":56,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,3,16]],"date-time":"2021-03-16T00:00:00Z","timestamp":1615852800000},"content-version":"vor","delay-in-days":74,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2018A030313318"],"award-info":[{"award-number":["2018A030313318"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>In order to alleviate the scale variation problem in object detection, many feature pyramid networks are developed. In this paper, we rethink the issues existing in current methods and design a more effective module for feature fusion, called multiflow feature fusion module (MF<jats:sup>3<\/jats:sup>M). We first construct gate modules and multiple information flows in MF<jats:sup>3<\/jats:sup>M to avoid information redundancy and enhance the completeness and accuracy of information transfer between feature maps. Furtherore, in order to reduce the discrepancy of classification and regression in object detection, a modified deformable convolution which is termed task adaptive convolution (TaConv) is proposed in this study. Different offsets and masks are predicted to achieve the disentanglement of features for classification and regression in TaConv. By integrating the above two designs, we build a novel feature pyramid network with feature fusion and disentanglement (FFAD) which can mitigate the scale misalignment and task misalignment simultaneously. Experimental results show that FFAD can boost the performance in most models.<\/jats:p>","DOI":"10.1155\/2021\/6685954","type":"journal-article","created":{"date-parts":[[2021,3,16]],"date-time":"2021-03-16T20:20:58Z","timestamp":1615926058000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["A Novel Pyramid Network with Feature Fusion and Disentanglement for Object Detection"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0494-3404","authenticated-orcid":false,"given":"Guoyi","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5076-8937","authenticated-orcid":false,"given":"You","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5242-7909","authenticated-orcid":false,"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4758-6091","authenticated-orcid":false,"given":"Yang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,3,16]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"crossref","unstructured":"SinghB.andDavisL. S. An analysis of scale invariance in object detection snip Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2018 Salt Lake City UT USA 3578\u20133587.","DOI":"10.1109\/CVPR.2018.00377"},{"key":"e_1_2_9_2_2","first-page":"21","article-title":"Ssd: single shot multibox detector","author":"Liu W.","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"e_1_2_9_3_2","doi-asserted-by":"crossref","unstructured":"LinT.-Yi Feature pyramid networks for object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition July 2017 Honolulu HI USA 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_2_9_4_2","doi-asserted-by":"crossref","unstructured":"WangK. Panet: few-shot image semantic segmentation with prototype alignment Proceedings of the IEEE International Conference on Computer Vision October 2019 Seoul South Korea 9197\u20139206.","DOI":"10.1109\/ICCV.2019.00929"},{"key":"e_1_2_9_5_2","doi-asserted-by":"crossref","unstructured":"TanM. PangR. andQuocV. Efficientdet: scalable and efficient object detection Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2020 Seattle WA USA 10781\u201310790.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"e_1_2_9_6_2","doi-asserted-by":"crossref","unstructured":"PangJ. Libra r-cnn: towards balanced learning for object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 821\u2013830.","DOI":"10.1109\/CVPR.2019.00091"},{"key":"e_1_2_9_7_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"WangX. Scale-equalizing pyramid convolution for object detection Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2020 Seattle WA USA 13359\u201313368.","DOI":"10.1109\/CVPR42600.2020.01337"},{"key":"e_1_2_9_9_2","doi-asserted-by":"crossref","unstructured":"JiangB. Acquisition of localization confidence for accurate object detection Proceedings of the European Conference on Computer Vision (ECCV) September 2018 Munich Germany 784\u2013799.","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"WuY. Rethinking classification and localization for object detection Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2020 Seattle WA USA 10186\u201310195.","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"e_1_2_9_11_2","doi-asserted-by":"crossref","unstructured":"SongG. LiuYu andWangX. Revisiting the sibling head in object detector Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2020 Seattle WA USA 11563\u201311572.","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"e_1_2_9_12_2","doi-asserted-by":"crossref","unstructured":"HuJ. ShenLi andSunG. Squeeze-and-excitation networks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2018 Salt Lake City UT USA 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_2_9_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_2_9_14_2","doi-asserted-by":"crossref","unstructured":"ZhuX. An empirical study of spatial attention mechanisms in deep networks Proceedings of the IEEE International Conference on Computer Vision October 2019 Seoul South Korea 6688\u20136697.","DOI":"10.1109\/ICCV.2019.00679"},{"key":"e_1_2_9_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3014312"},{"key":"e_1_2_9_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/lgrs.2020.3017233"},{"key":"e_1_2_9_17_2","unstructured":"SunR. Rich feature hierarchies for accurate object detection and semantic segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2014 Columbus OH USA 580\u2013587."},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"GirshickR. Fast R-CNN Proceedings of the IEEE International Conference on Computer Vision September 2015 Santiago Chile 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_2_9_19_2","first-page":"91","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","author":"Ren S.","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_20_2","first-page":"379","article-title":"R-FCN: object detection via region-based fully convolutional networks","author":"Dai J.","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_21_2","doi-asserted-by":"crossref","unstructured":"HeK. Mask R-CNN Proceedings of the IEEE International Conference on Computer Vision October 2017 Venice Italy 2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_2_9_22_2","doi-asserted-by":"crossref","unstructured":"RedmonJ. You only look once: unified real-time object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2016 Las Vegas NV USA 779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_2_9_23_2","doi-asserted-by":"crossref","unstructured":"RedmonJ.andAliF. YOLO9000: better faster stronger Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition July 2017 Honolulu HI USA 7263\u20137271.","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_2_9_24_2","unstructured":"RedmonJ.andAliF. Yolov3: an incremental improvement 2018 http:\/\/arxiv.org\/abs\/1804.02767."},{"key":"e_1_2_9_25_2","doi-asserted-by":"crossref","unstructured":"LinT.-Y. Focal loss for dense object detection Proceedings of the IEEE International Conference on Computer Vision October 2017 Venice Italy 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_2_9_26_2","doi-asserted-by":"crossref","unstructured":"TianZ. FCOS: fully convolutional one-stage object detection Proceedings of the IEEE International Conference on Computer Vision October 2019 Seoul South Korea 9627\u20139636.","DOI":"10.1109\/ICCV.2019.00972"},{"key":"e_1_2_9_27_2","doi-asserted-by":"crossref","unstructured":"ZhuC. HeY. andSavvidesM. Feature selective anchor-free module for single-shot object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 840\u2013849.","DOI":"10.1109\/CVPR.2019.00093"},{"key":"e_1_2_9_28_2","doi-asserted-by":"crossref","unstructured":"ZhangS. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2020 Seattle WA USA 9759\u20139768.","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"e_1_2_9_29_2","unstructured":"SinghB. NajibiM. LarryS. andDavis Sniper: efficient multi-scale training Proceedings of the Advances in Neural Information Processing Systems December 2018 Montreal Canada 9310\u20139320."},{"key":"e_1_2_9_30_2","doi-asserted-by":"crossref","unstructured":"LiuS.andHuangD. Receptive field block net for accurate and fast object detection Proceedings of the European Conference on Computer Vision (ECCV) September 2018 Munich Germany 385\u2013400.","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"e_1_2_9_31_2","first-page":"483","article-title":"Stacked hourglass networks for human pose estimation","author":"Newell A.","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"e_1_2_9_32_2","doi-asserted-by":"crossref","unstructured":"SunKe Deep high-resolution representation learning for human pose estimation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 5693\u20135703.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_2_9_33_2","doi-asserted-by":"crossref","unstructured":"ZhangH.andWangJ. Towards adversarially robust object detection Proceedings of the IEEE International Conference on Computer Vision November 2019 Seoul South Korea 421\u2013430.","DOI":"10.1109\/ICCV.2019.00051"},{"key":"e_1_2_9_34_2","doi-asserted-by":"crossref","unstructured":"ZhuX. Deformable convnets v2: more deformable better results Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 9308\u20139316.","DOI":"10.1109\/CVPR.2019.00953"},{"key":"e_1_2_9_35_2","first-page":"740","article-title":"Microsoft coco: common objects in context","author":"Lin T.-Yi","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"e_1_2_9_36_2","doi-asserted-by":"crossref","unstructured":"LuX. Grid R-CNN Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 7363\u20137372.","DOI":"10.1109\/CVPR.2019.00754"},{"key":"e_1_2_9_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_2_9_38_2","doi-asserted-by":"crossref","unstructured":"HeK. Deep residual learning for image recognition Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition July 2016 Las Vegas NV USA 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_39_2","doi-asserted-by":"crossref","unstructured":"GhiasiG. LinT.-Yi QuocV. andLe Nas-Fpn: learning scalable feature pyramid architecture for object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 7036\u20137045.","DOI":"10.1109\/CVPR.2019.00720"},{"key":"e_1_2_9_40_2","doi-asserted-by":"crossref","unstructured":"DaiJ. Deformable convolutional networks Proceedings of the IEEE International Conference on Computer Vision October 2017 Venice Italy 764\u2013773.","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_2_9_41_2","doi-asserted-by":"crossref","unstructured":"BodlaN. Soft-NMS--improving object detection with one line of code Proceedings of the IEEE International Conference on Computer Vision October 2017 Venice Italy 5561\u20135569.","DOI":"10.1109\/ICCV.2017.593"},{"key":"e_1_2_9_42_2","doi-asserted-by":"crossref","unstructured":"BaiY. Sod-MTGAN: small object detection via multi-task generative adversarial network Proceedings of the European Conference on Computer Vision (ECCV) September 2018 Munich Germany 206\u2013221.","DOI":"10.1007\/978-3-030-01261-8_13"},{"key":"e_1_2_9_43_2","doi-asserted-by":"crossref","unstructured":"CaiZ.andVasconcelosN. Cascade R-CNN: delving into high quality object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2018 Salt Lake City UT USA 6154\u20136162.","DOI":"10.1109\/CVPR.2018.00644"},{"key":"e_1_2_9_44_2","doi-asserted-by":"crossref","unstructured":"LiY. Scale-aware trident networks for object detection Proceedings of the IEEE International Conference on Computer Vision November 2019 Seoul South Korea 6054\u20136063.","DOI":"10.1109\/ICCV.2019.00615"},{"key":"e_1_2_9_45_2","unstructured":"FuC.-Y. DSSD: deconvolutional single shot detector 2017 http:\/\/arxiv.org\/abs\/1701.06659."},{"key":"e_1_2_9_46_2","doi-asserted-by":"crossref","unstructured":"ZhangS. Single-shot refinement neural network for object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2018 Salt Lake City UT USA 4203\u20134212.","DOI":"10.1109\/CVPR.2018.00442"},{"key":"e_1_2_9_47_2","doi-asserted-by":"crossref","unstructured":"SametN. HicsonmezS. andAkbasE. Reducing label noise in anchor-free object detection 2020 http:\/\/arxiv.org\/abs\/2008.01167.","DOI":"10.1186\/s13640-020-00517-3"},{"key":"e_1_2_9_48_2","doi-asserted-by":"crossref","unstructured":"XuH. Auto-FPN: automatic network architecture adaptation for object detection beyond classification Proceedings of the IEEE International Conference on Computer Vision November 2019 Seoul South Korea 6649\u20136658.","DOI":"10.1109\/ICCV.2019.00675"},{"key":"e_1_2_9_49_2","first-page":"147","article-title":"Freeanchor: learning to match anchors for visual object detection","author":"Zhang X.","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2020.3002345"},{"key":"e_1_2_9_51_2","doi-asserted-by":"crossref","unstructured":"LawH.andJiaD. Cornernet: detecting objects as paired keypoints Proceedings of the European Conference on Computer Vision (ECCV) September 2018 Munich Germany 734\u2013750.","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"e_1_2_9_52_2","doi-asserted-by":"crossref","unstructured":"ZhouX. ZhuoJ. andKrahenbuhlP. Bottom-up object detection by grouping extreme and center points Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2019 Long Beach CA USA 850\u2013859.","DOI":"10.1109\/CVPR.2019.00094"},{"key":"e_1_2_9_53_2","doi-asserted-by":"crossref","unstructured":"DuanK. Centernet: keypoint triplets for object detection Proceedings of the IEEE International Conference on Computer Vision November 2019 Seoul South Korea 6569\u20136578.","DOI":"10.1109\/ICCV.2019.00667"},{"key":"e_1_2_9_54_2","doi-asserted-by":"crossref","unstructured":"YangZ. Reppoints: point set representation for object detection Proceedings of the IEEE International Conference on Computer Vision November 2019 Seoul South Korea 9657\u20139666.","DOI":"10.1109\/ICCV.2019.00975"},{"key":"e_1_2_9_55_2","doi-asserted-by":"crossref","unstructured":"DavidE. Global Wheat Head Detection (GWHD) dataset: a large and diverse dataset of high resolution RGB labelled images to develop and benchmark wheat head detection methods 2020 http:\/\/arxiv.org\/abs\/2005.02162.","DOI":"10.34133\/2020\/3521852"},{"key":"e_1_2_9_56_2","volume-title":"ultralytics\/yolov5: v3.1-Bug Fixes and Performance Improvements (Version v3.1)","author":"Jocher G.","year":"2020"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/6685954.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/6685954.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/6685954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T12:29:23Z","timestamp":1722947363000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/6685954"}},"subtitle":[],"editor":[{"given":"Qiangqiang","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/6685954"],"URL":"https:\/\/doi.org\/10.1155\/2021\/6685954","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"value":"1687-5265","type":"print"},{"value":"1687-5273","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2020-10-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"6685954"}}