{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T17:49:24Z","timestamp":1783619364748,"version":"3.55.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Huawei"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tpami.2023.3286109","type":"journal-article","created":{"date-parts":[[2023,6,14]],"date-time":"2023-06-14T17:22:03Z","timestamp":1686763323000},"page":"12269-12286","source":"Crossref","is-referenced-by-count":13,"title":["PWLU: Learning Specialized Activation Functions With the Piecewise Linear Unit"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0341-6584","authenticated-orcid":false,"given":"Zezhou","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0484-8215","authenticated-orcid":false,"given":"Yucong","family":"Zhou","sequence":"additional","affiliation":[{"name":"2012 Labs, Huawei Technologies Co Ltd, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8650-1603","authenticated-orcid":false,"given":"Yuan","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2758-706X","authenticated-orcid":false,"given":"Zhao","family":"Zhong","sequence":"additional","affiliation":[{"name":"2012 Labs, Huawei Technologies Co Ltd, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref56","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01188"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref52","article-title":"Mixup: Beyond empirical risk minimization","author":"zhang","year":"2017"},{"key":"ref11","article-title":"Padé activation units: End-to-end learning of flexible activation functions in deep networks","author":"molina","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref55","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref10","article-title":"Learning activation functions to improve deep neural networks","author":"agostinelli","year":"2014"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3302"},{"key":"ref17","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","author":"pham","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2969193"},{"key":"ref19","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"cai","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref18","article-title":"DARTS: Differentiable architecture search","author":"liu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref51","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","article-title":"Gaussian error linear units (GELUs)","author":"hendrycks","year":"2016"},{"key":"ref46","article-title":"XCiT: Cross-covariance image transformers","author":"el-nouby","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref48","article-title":"LocalViT: Bringing locality to vision transformers","author":"li","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref44","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref8","first-page":"971","article-title":"Self-normalizing neural networks","author":"klambauer","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","author":"clevert","year":"2015"},{"key":"ref9","article-title":"Searching for activation functions","author":"ramachandran","year":"2017"},{"key":"ref4","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","first-page":"807","article-title":"Rectified linear units improve restricted BoltzMann machines","author":"nair","year":"2010","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref5","article-title":"Rectifier nonlinearities improve neural network acoustic models","author":"maas","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref40","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","article-title":"Adversarial autoaugment","author":"zhang","year":"2019"},{"key":"ref34","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","first-page":"32","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/35016072"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref24","article-title":"Highway networks","author":"srivastava","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref26","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","first-page":"4790","article-title":"Conditional image generation with PixelCNN decoders","author":"van den oord","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","article-title":"Activate or not: Learning customized activation","author":"ma","year":"2020"},{"key":"ref22","first-page":"1319","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2541681"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_21"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_21"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10241246\/10151955.pdf?arnumber=10151955","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T17:12:50Z","timestamp":1717693970000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10151955\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":56,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3286109","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}