{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/activate-or-not-learning-customized","title":"Activate or Not: Learning Customized Activation","arxiv_id":"2009.04759","date":"2020-09-10","proceeding":"CVPR 2021 1","authors":["Ningning Ma","Xiangyu Zhang","Ming Liu","Jian Sun"],"abstract":"We present a simple, effective, and general activation function we term ACON which learns to activate the neurons or not. Interestingly, we find Swish, the recent popular NAS-searched activation, can be interpreted as a smooth approximation to ReLU. Intuitively, in the same way, we approximate the more general Maxout family to our novel ACON family, which remarkably improves the performance and makes Swish a special case of ACON. Next, we present meta-ACON, which explicitly learns to optimize the parameter switching between non-linear (activate) and linear (inactivate) and provides a new design space. By simply changing the activation function, we show its effectiveness on both small models and highly optimized large models (e.g. it improves the ImageNet top-1 accuracy rate by 6.7% and 1.8% on MobileNet-0.25 and ResNet-152, respectively). Moreover, our novel ACON can be naturally transferred to object detection and semantic segmentation, showing that ACON is an effective alternative in a variety of tasks. Code is available at https://github.com/nmaac/acon.","url_abs":"https://arxiv.org/abs/2009.04759v2","url_pdf":"https://arxiv.org/pdf/2009.04759v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"activate-or-not-learning-customized","repo_url":"https://github.com/nmaac/acon","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"activate-or-not-learning-customized","repo_url":"https://github.com/DeadNud1e/Acon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"activate-or-not-learning-customized","repo_url":"https://github.com/littletomatodonkey/code_scipts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"unanswered"}},{"paper_slug":"activate-or-not-learning-customized","repo_url":"https://github.com/xdhe1216/ACON","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"activate-or-not-learning-customized","repo_url":"https://github.com/qwopqwop200/acon-tf2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"maxout","method_name":"Maxout"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.04759","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}