{"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/incorporating-transformer-designs-into","title":"Incorporating Transformer Designs into Convolutions for Lightweight Image Super-Resolution","arxiv_id":"2303.14324","date":"2023-03-25","proceeding":null,"authors":["Gang Wu","Junjun Jiang","Yuanchao Bai","Xianming Liu"],"abstract":"In recent years, the use of large convolutional kernels has become popular in designing convolutional neural networks due to their ability to capture long-range dependencies and provide large receptive fields. However, the increase in kernel size also leads to a quadratic growth in the number of parameters, resulting in heavy computation and memory requirements. To address this challenge, we propose a neighborhood attention (NA) module that upgrades the standard convolution with a self-attention mechanism. The NA module efficiently extracts long-range dependencies in a sliding window pattern, thereby achieving similar performance to large convolutional kernels but with fewer parameters. Building upon the NA module, we propose a lightweight single image super-resolution (SISR) network named TCSR. Additionally, we introduce an enhanced feed-forward network (EFFN) in TCSR to improve the SISR performance. EFFN employs a parameter-free spatial-shift operation for efficient feature aggregation. Our extensive experiments and ablation studies demonstrate that TCSR outperforms existing lightweight SISR methods and achieves state-of-the-art performance. Our codes are available at \\url{https://github.com/Aitical/TCSR}.","url_abs":"https://arxiv.org/abs/2303.14324v1","url_pdf":"https://arxiv.org/pdf/2303.14324v1.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":"incorporating-transformer-designs-into","repo_url":"https://github.com/aitical/tcsr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"na","method_name":"Neighborhood Attention"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.14324","atlas_url":"https://app.syntology.ai/?focus=2303.14324","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}