{"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/vne-an-effective-method-for-improving-deep","title":"VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution","arxiv_id":"2304.01434","date":"2023-04-04","proceeding":"CVPR 2023 1","authors":["Jaeill Kim","Suhyun Kang","Duhun Hwang","Jungwook Shin","Wonjong Rhee"],"abstract":"Since the introduction of deep learning, a wide scope of representation properties, such as decorrelation, whitening, disentanglement, rank, isotropy, and mutual information, have been studied to improve the quality of representation. However, manipulating such properties can be challenging in terms of implementational effectiveness and general applicability. To address these limitations, we propose to regularize von Neumann entropy~(VNE) of representation. First, we demonstrate that the mathematical formulation of VNE is superior in effectively manipulating the eigenvalues of the representation autocorrelation matrix. Then, we demonstrate that it is widely applicable in improving state-of-the-art algorithms or popular benchmark algorithms by investigating domain-generalization, meta-learning, self-supervised learning, and generative models. In addition, we formally establish theoretical connections with rank, disentanglement, and isotropy of representation. Finally, we provide discussions on the dimension control of VNE and the relationship with Shannon entropy. Code is available at: https://github.com/jaeill/CVPR23-VNE.","url_abs":"https://arxiv.org/abs/2304.01434v1","url_pdf":"https://arxiv.org/pdf/2304.01434v1.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":"vne-an-effective-method-for-improving-deep","repo_url":"https://github.com/jaeill/CVPR23-VNE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-office-home","task":"Domain Generalization","dataset":"Office-Home","model":"VNE (ResNet-50, SWAD)","rank_in_archive_order":28,"of":45,"metrics":{"Average Accuracy":"71.1"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"VNE (ResNet-50, SWAD)","rank_in_archive_order":30,"of":133,"metrics":{"Average Accuracy":"88.3"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-terraincognita","task":"Domain Generalization","dataset":"TerraIncognita","model":"VNE (ResNet-50, SWAD)","rank_in_archive_order":20,"of":30,"metrics":{"Average Accuracy":"51.7"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vlcs","task":"Domain Generalization","dataset":"VLCS","model":"VNE (ResNet-50, SWAD)","rank_in_archive_order":22,"of":37,"metrics":{"Average Accuracy":"79.7"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"VNE (BOIL)","rank_in_archive_order":97,"of":105,"metrics":{"Accuracy":"50.95"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-3","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"VNE (BOIL)","rank_in_archive_order":87,"of":95,"metrics":{"Accuracy":"67.52"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"I-VNE+ (ResNet-50)","rank_in_archive_order":95,"of":144,"metrics":{"Number of Params":"25M","Top 1 Accuracy":"72.1","Top 5 Accuracy":"91.0"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"I-VNE+ (ResNet-50)","rank_in_archive_order":45,"of":65,"metrics":{"Top 1 Accuracy":"55.8","Top 5 Accuracy":"81.0"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"I-VNE+ (ResNet-50)","rank_in_archive_order":42,"of":75,"metrics":{"Top 1 Accuracy":"69.1","Top 5 Accuracy":"89.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.01434","atlas_url":"https://app.syntology.ai/?focus=2304.01434","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":"2304.01434"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2304.01434\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2304.01434"},"call":"get_concepts_for_paper(arxiv_id=\"2304.01434\")"}],"by_repo":[{"repo":"jaeill/CVPR23-VNE","kind":"official","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":"417334db410feb884df6795f881c9e5bff886cf8f49faf4d90ddfee322bb96e7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}