{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/towards-image-understanding-from-deep","title":"Towards Image Understanding from Deep Compression without Decoding","arxiv_id":"1803.06131","date":"2018-03-16","proceeding":"ICLR 2018 1","authors":["Robert Torfason","Fabian Mentzer","Eirikur Agustsson","Michael Tschannen","Radu Timofte","Luc van Gool"],"abstract":"Motivated by recent work on deep neural network (DNN)-based image compression\nmethods showing potential improvements in image quality, savings in storage,\nand bandwidth reduction, we propose to perform image understanding tasks such\nas classification and segmentation directly on the compressed representations\nproduced by these compression methods. Since the encoders and decoders in\nDNN-based compression methods are neural networks with feature-maps as internal\nrepresentations of the images, we directly integrate these with architectures\nfor image understanding. This bypasses decoding of the compressed\nrepresentation into RGB space and reduces computational cost. Our study shows\nthat accuracies comparable to networks that operate on compressed RGB images\ncan be achieved while reducing the computational complexity up to $2\\times$.\nFurthermore, we show that synergies are obtained by jointly training\ncompression networks with classification networks on the compressed\nrepresentations, improving image quality, classification accuracy, and\nsegmentation performance. We find that inference from compressed\nrepresentations is particularly advantageous compared to inference from\ncompressed RGB images for aggressive compression rates.","url_abs":"http://arxiv.org/abs/1803.06131v1","url_pdf":"http://arxiv.org/pdf/1803.06131v1.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":"towards-image-understanding-from-deep","repo_url":"https://github.com/pkorus/l3ic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-compression","task_name":"Image Compression"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.06131","atlas_url":"https://app.syntology.ai/?focus=1803.06131","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1803.06131"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1803.06131\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1803.06131"},"call":"get_concepts_for_paper(arxiv_id=\"1803.06131\")"}],"by_repo":[{"repo":"pkorus/l3ic","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"6f96054b0ae83e6514cc500193b32d0b4917d86044731d8038fddfc5aa4d7405","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}