{"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/dsslic-deep-semantic-segmentation-based","title":"DSSLIC: Deep Semantic Segmentation-based Layered Image Compression","arxiv_id":"1806.03348","date":"2018-06-08","proceeding":null,"authors":["Mohammad Akbari","Jie Liang","Jingning Han"],"abstract":"Deep learning has revolutionized many computer vision fields in the last few\nyears, including learning-based image compression. In this paper, we propose a\ndeep semantic segmentation-based layered image compression (DSSLIC) framework\nin which the semantic segmentation map of the input image is obtained and\nencoded as the base layer of the bit-stream. A compact representation of the\ninput image is also generated and encoded as the first enhancement layer. The\nsegmentation map and the compact version of the image are then employed to\nobtain a coarse reconstruction of the image. The residual between the input and\nthe coarse reconstruction is additionally encoded as another enhancement layer.\nExperimental results show that the proposed framework outperforms the\nH.265/HEVC-based BPG and other codecs in both PSNR and MS-SSIM metrics across a\nwide range of bit rates in RGB domain. Besides, since semantic segmentation map\nis included in the bit-stream, the proposed scheme can facilitate many other\ntasks such as image search and object-based adaptive image compression.","url_abs":"http://arxiv.org/abs/1806.03348v3","url_pdf":"http://arxiv.org/pdf/1806.03348v3.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":"dsslic-deep-semantic-segmentation-based","repo_url":"https://github.com/makbari7/DSSLIC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dsslic-deep-semantic-segmentation-based","repo_url":"https://github.com/Iamanorange/DSSLIC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-compression","task_name":"Image Compression"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"ms-ssim","task_name":"MS-SSIM"},{"task_slug":"ssim","task_name":"SSIM"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.03348","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}