{"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/adanic-towards-practical-neural-image","title":"AdaNIC: Towards Practical Neural Image Compression via Dynamic Transform Routing","arxiv_id":null,"date":"2023-01-01","proceeding":"ICCV 2023 1","authors":["Lvfang Tao","Wei Gao","Ge Li","Chenhao Zhang"],"abstract":"    Compressive autoencoders (CAEs) play an important role in deep learning-based image compression, but large-scale CAEs are computationally expensive. We propose a framework with three techniques to enable efficient CAE-based image coding: 1) Spatially-adaptive convolution and normalization operators enable block-wise nonlinear transform to spend FLOPs unevenly across the image to be compressed, according to a transform capacity map. 2) Just-unpenalized model capacity (JUMC) optimizes the transform capacity of each CAE block via rate-distortion-complexity optimization, finding the optimal capacity for the source image content. 3) A lightweight routing agent model predicts the transform capacity map for the CAEs by approximating JUMC targets. By activating the best-sized sub-CAE inside the slimmable supernet, our approach achieves up to 40% computational speed-up with minimal BD-Rate increase, validating its ability to save computational resources in a content-aware manner.    ","url_abs":"http://openaccess.thecvf.com//content/ICCV2023/html/Tao_AdaNIC_Towards_Practical_Neural_Image_Compression_via_Dynamic_Transform_Routing_ICCV_2023_paper.html","url_pdf":"http://openaccess.thecvf.com//content/ICCV2023/papers/Tao_AdaNIC_Towards_Practical_Neural_Image_Compression_via_Dynamic_Transform_Routing_ICCV_2023_paper.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":"adanic-towards-practical-neural-image","repo_url":"https://github.com/2024-MindSpore-1/Code10/tree/main/adanic-mindspore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"adanic-towards-practical-neural-image","repo_url":"https://github.com/yangyucheng000/Paper-3/tree/main/adanic-mindspore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"image-compression","task_name":"Image Compression"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}