{"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/on-disentangled-training-for-nonlinear","title":"On Disentangled Training for Nonlinear Transform in Learned Image Compression","arxiv_id":"2501.13751","date":"2025-01-23","proceeding":null,"authors":["Han Li","Shaohui Li","Wenrui Dai","Maida Cao","Nuowen Kan","Chenglin Li","Junni Zou","Hongkai Xiong"],"abstract":"Learned image compression (LIC) has demonstrated superior rate-distortion (R-D) performance compared to traditional codecs, but is challenged by training inefficiency that could incur more than two weeks to train a state-of-the-art model from scratch. Existing LIC methods overlook the slow convergence caused by compacting energy in learning nonlinear transforms. In this paper, we first reveal that such energy compaction consists of two components, i.e., feature decorrelation and uneven energy modulation. On such basis, we propose a linear auxiliary transform (AuxT) to disentangle energy compaction in training nonlinear transforms. The proposed AuxT obtains coarse approximation to achieve efficient energy compaction such that distribution fitting with the nonlinear transforms can be simplified to fine details. We then develop wavelet-based linear shortcuts (WLSs) for AuxT that leverages wavelet-based downsampling and orthogonal linear projection for feature decorrelation and subband-aware scaling for","url_abs":"https://arxiv.org/abs/2501.13751v3","url_pdf":"https://arxiv.org/pdf/2501.13751v3.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":"on-disentangled-training-for-nonlinear","repo_url":"https://github.com/qingshi9974/auxt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-compression","task_name":"Image Compression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.13751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13751"}},"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/qingshi9974/auxt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"1eca81f63e28f103","entry":"get_scale_table","repo":"qingshi9974/auxt","repo_kind":"official","path":"models/tcm.py","file_url":"https://github.com/qingshi9974/auxt/blob/HEAD/models/tcm.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1eca81f63e28f103"}},{"code_sha256_prefix":"cd3178f088f029d1","entry":"ste_round","repo":"qingshi9974/auxt","repo_kind":"official","path":"models/tcm_AuxT.py","file_url":"https://github.com/qingshi9974/auxt/blob/HEAD/models/tcm_AuxT.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd3178f088f029d1"}},{"code_sha256_prefix":"15eae621014906be","entry":"conv1x1","repo":"qingshi9974/auxt","repo_kind":"official","path":"models/tcm.py","file_url":"https://github.com/qingshi9974/auxt/blob/HEAD/models/tcm.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"15eae621014906be"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}