{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:04:37Z","timestamp":1753884277329,"version":"3.41.2"},"reference-count":25,"publisher":"World Scientific Pub Co Pte Ltd","issue":"08","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62236007"],"award-info":[{"award-number":["62236007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2023,6,30]]},"abstract":"<jats:p> In recent years, super-resolution neural networks have achieved good results in restoring super-resolution images from low-resolution ones. However, most subsequent tasks based on super-resolution images such as object detection are done by the computer. Considering this situation, we propose a learnable downsampler\u2013upsampler pair, which can realize both the downscaling process and the upscaling process by neural networks, and is jointly trained with the YOLOV5 network to optimize the object detection task. Thus, different from existing super-resolution networks, the entire downsampler\u2013upsampler pair is optimized for machine perception. In addition, to further reduce the size of the downsampled images, we also propose a differentiable method for estimating image entropy and add it to the loss function. We verify the effectiveness of our method on the pothole dataset and use scale factors 2\u00d7 and 4\u00d7 to prove that our method is capable of diverse resizing levels. The experimental results show that using our learnable downsampler\u2013upsampler pair as a resizing method can highly improve the detection performance compared with other resizing techniques. <\/jats:p>","DOI":"10.1142\/s0218001423540113","type":"journal-article","created":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T08:47:28Z","timestamp":1685004448000},"source":"Crossref","is-referenced-by-count":0,"title":["Image Resizing for Object Detection: A Learnable Downsampler\u2013Upsampler Pair with Differentiable Image Entropy Estimation"],"prefix":"10.1142","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5750-1007","authenticated-orcid":false,"given":"Chengjie","family":"Dai","sequence":"first","affiliation":[{"name":"School of Aeronautics and Astronautics, Zhejiang University, No. 38, Zheda Road, Xihu District, Hangzhou, Zhejiang 310013, P.\u00a0R.\u00a0China"},{"name":"Huanjiang Laboratory, Zhuji, Zhejiang 311800, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai FinShine Technology Ltd., No. 65, Jinqiao Road, Pudong New District, Shanghai 201203, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingchao","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, Zhejiang University, No. 38, Zheda Road, Xihu District, Hangzhou, Zhejiang 310013, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanshen","family":"Gong","sequence":"additional","affiliation":[{"name":"Shanghai FinShine Technology Ltd., No. 65, Jinqiao Road, Pudong New District, Shanghai 201203, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanghua","family":"Song","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, Zhejiang University, No. 38, Zheda Road, Xihu District, Hangzhou, Zhejiang 310013, P.\u00a0R.\u00a0China"},{"name":"Huanjiang Laboratory, Zhuji, Zhejiang 311800, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8581-3817","authenticated-orcid":false,"given":"Bowei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, Zhejiang University, No. 38, Zheda Road, Xihu District, Hangzhou, Zhejiang 310013, P.\u00a0R.\u00a0China"},{"name":"Huanjiang Laboratory, Zhuji, Zhejiang 311800, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2023,6,16]]},"reference":[{"key":"S0218001423540113BIB001","first-page":"1141","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Agustsson E.","year":"2017"},{"key":"S0218001423540113BIB002","series-title":"Lecture Notes in Computer Science","first-page":"252","volume-title":"ECCV 2018: Computer Vision","volume":"11214","author":"Ahn N.","year":"2018"},{"key":"S0218001423540113BIB003","series-title":"Lecture Notes in Computer Science","first-page":"206","volume-title":"ECCV 2018: Computer Vision","volume":"11217","author":"Bai Y.","year":"2018"},{"key":"S0218001423540113BIB005","first-page":"1440","volume-title":"Proc. 2015 IEEE Int. Conf. Computer Vision","author":"Girshick R.","year":"2015"},{"key":"S0218001423540113BIB006","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1109\/CVPR.2014.81","volume-title":"Proc. 2014 IEEE Conf. Computer Vision and Pattern Recognition","author":"Girshick R.","year":"2014"},{"key":"S0218001423540113BIB007","first-page":"2672","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Goodfellow I.","year":"2014"},{"key":"S0218001423540113BIB008","series-title":"Communications in Computer and Information Science","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1007\/978-3-030-92307-5_45","volume-title":"ICONIP 2021: Neural Information Processing","volume":"1516","author":"Haris M.","year":"2021"},{"key":"S0218001423540113BIB009","first-page":"770","volume-title":"Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition","author":"He K.","year":"2016"},{"key":"S0218001423540113BIB010","first-page":"448","volume":"37","author":"Ioffe S.","year":"2015","journal-title":"Proc. Mach. Learn. Res."},{"volume-title":"Proc. 2019 Int. Conf. Learning Representations","year":"2019","author":"Jolicoeur-Martineau A.","key":"S0218001423540113BIB012"},{"key":"S0218001423540113BIB013","first-page":"1646","volume-title":"Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition","author":"Kim J.","year":"2016"},{"key":"S0218001423540113BIB014","first-page":"4681","volume-title":"Proc. 2017 IEEE Conf. Computer Vision and Pattern Recognition","author":"Ledig C.","year":"2017"},{"key":"S0218001423540113BIB015","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"ECCV 2016: Computer Vision","volume":"9905","author":"Liu W.","year":"2016"},{"key":"S0218001423540113BIB016","first-page":"10096","volume-title":"Proc. 2020 IEEE\/CVF Conf. Computer Vision and Pattern Recognition","author":"Liu J.-J.","year":"2020"},{"volume-title":"Proc. 2015 IEEE Symp. Series on Computational Intelligence","year":"2015","author":"Nienaber S.","key":"S0218001423540113BIB017"},{"key":"S0218001423540113BIB018","doi-asserted-by":"crossref","first-page":"1432","DOI":"10.3390\/rs12091432","volume":"12","author":"Rabbi J.","year":"2020","journal-title":"Remote Sens."},{"key":"S0218001423540113BIB019","first-page":"779","volume-title":"Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition","author":"Redmon J.","year":"2016"},{"key":"S0218001423540113BIB020","first-page":"91","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Ren S.","year":"2015"},{"volume-title":"Proc. 2019 IEEE\/CVF Conf. Computer Vision and Pattern Recognition Workshops","year":"2019","author":"Shermeyer J.","key":"S0218001423540113BIB021"},{"key":"S0218001423540113BIB022","first-page":"497","volume-title":"Proc. 2021 IEEE\/CVF Int. Conf. Computer Vision","author":"Talebi H.","year":"2021"},{"volume-title":"Proc. Int. Conf. Learning Representations (ICLR 2017)","year":"2017","author":"Theis L.","key":"S0218001423540113BIB023"},{"volume-title":"Elements of Information Theory","year":"2006","author":"Thomas M.","key":"S0218001423540113BIB024"},{"key":"S0218001423540113BIB025","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/978-3-030-11021-5_5","volume-title":"ECCV 2018: Computer Vision","volume":"11133","author":"Wang X.","year":"2018"},{"key":"S0218001423540113BIB026","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1007\/978-3-319-96890-2_24","volume-title":"ECCV 2018: Computer Vision","volume":"11211","author":"Zhang Y.","year":"2018"},{"key":"S0218001423540113BIB027","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1007\/978-3-030-67070-2_3","volume-title":"ECCV 2020: Computer Vision","volume":"12537","author":"Zhao H.","year":"2020"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001423540113","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T06:33:29Z","timestamp":1690353209000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0218001423540113"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,16]]},"references-count":25,"journal-issue":{"issue":"08","published-print":{"date-parts":[[2023,6,30]]}},"alternative-id":["10.1142\/S0218001423540113"],"URL":"https:\/\/doi.org\/10.1142\/s0218001423540113","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"type":"print","value":"0218-0014"},{"type":"electronic","value":"1793-6381"}],"subject":[],"published":{"date-parts":[[2023,6,16]]},"article-number":"2354011"}}