{"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/learning-convolutional-networks-for-content","title":"Learning Convolutional Networks for Content-weighted Image Compression","arxiv_id":"1703.10553","date":"2017-03-30","proceeding":"CVPR 2018 6","authors":["Mu Li","WangMeng Zuo","Shuhang Gu","Debin Zhao","David Zhang"],"abstract":"Lossy image compression is generally formulated as a joint rate-distortion\noptimization to learn encoder, quantizer, and decoder. However, the quantizer\nis non-differentiable, and discrete entropy estimation usually is required for\nrate control. These make it very challenging to develop a convolutional network\n(CNN)-based image compression system. In this paper, motivated by that the\nlocal information content is spatially variant in an image, we suggest that the\nbit rate of the different parts of the image should be adapted to local\ncontent. And the content aware bit rate is allocated under the guidance of a\ncontent-weighted importance map. Thus, the sum of the importance map can serve\nas a continuous alternative of discrete entropy estimation to control\ncompression rate. And binarizer is adopted to quantize the output of encoder\ndue to the binarization scheme is also directly defined by the importance map.\nFurthermore, a proxy function is introduced for binary operation in backward\npropagation to make it differentiable. Therefore, the encoder, decoder,\nbinarizer and importance map can be jointly optimized in an end-to-end manner\nby using a subset of the ImageNet database. In low bit rate image compression,\nexperiments show that our system significantly outperforms JPEG and JPEG 2000\nby structural similarity (SSIM) index, and can produce the much better visual\nresult with sharp edges, rich textures, and fewer artifacts.","url_abs":"http://arxiv.org/abs/1703.10553v2","url_pdf":"http://arxiv.org/pdf/1703.10553v2.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":"learning-convolutional-networks-for-content","repo_url":"https://github.com/adityassrana/Content-Weighted-Image-Compression","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"binarization","task_name":"Binarization"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-compression","task_name":"Image Compression"},{"task_slug":"ssim","task_name":"SSIM"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.10553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.10553"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/adityassrana/Content-Weighted-Image-Compression","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"ran_violates":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"d7762cd765931380","entry":"bin_values","repo":"adityassrana/Content-Weighted-Image-Compression","repo_kind":"listed","path":"models.py","file_url":"https://github.com/adityassrana/Content-Weighted-Image-Compression/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d7762cd765931380"}},{"code_sha256_prefix":"8bc496012a56fcbf","entry":"conv","repo":"adityassrana/Content-Weighted-Image-Compression","repo_kind":"listed","path":"models.py","file_url":"https://github.com/adityassrana/Content-Weighted-Image-Compression/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8bc496012a56fcbf"}},{"code_sha256_prefix":"74d9d2fcc53cd0e2","entry":"quantize_values","repo":"adityassrana/Content-Weighted-Image-Compression","repo_kind":"listed","path":"models.py","file_url":"https://github.com/adityassrana/Content-Weighted-Image-Compression/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"74d9d2fcc53cd0e2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}