{"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/shape-adaptor-a-learnable-resizing-module","title":"Shape Adaptor: A Learnable Resizing Module","arxiv_id":"2008.00892","date":"2020-08-03","proceeding":"ECCV 2020 8","authors":["Shikun Liu","Zhe Lin","Yilin Wang","Jianming Zhang","Federico Perazzi","Edward Johns"],"abstract":"We present a novel resizing module for neural networks: shape adaptor, a drop-in enhancement built on top of traditional resizing layers, such as pooling, bilinear sampling, and strided convolution. Whilst traditional resizing layers have fixed and deterministic reshaping factors, our module allows for a learnable reshaping factor. Our implementation enables shape adaptors to be trained end-to-end without any additional supervision, through which network architectures can be optimised for each individual task, in a fully automated way. We performed experiments across seven image classification datasets, and results show that by simply using a set of our shape adaptors instead of the original resizing layers, performance increases consistently over human-designed networks, across all datasets. Additionally, we show the effectiveness of shape adaptors on two other applications: network compression and transfer learning. The source code is available at: https://github.com/lorenmt/shape-adaptor.","url_abs":"https://arxiv.org/abs/2008.00892v2","url_pdf":"https://arxiv.org/pdf/2008.00892v2.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":"shape-adaptor-a-learnable-resizing-module","repo_url":"https://github.com/lorenmt/shape-adaptor","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"automl","task_name":"AutoML"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"shape-adaptor","method_name":"Shape Adaptor"}],"datasets_introduced":[],"methods_introduced":[{"slug":"shape-adaptor","name":"Shape Adaptor","full_name":"Shape Adaptor"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2008.00892","atlas_url":"https://app.syntology.ai/?focus=2008.00892","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}