{"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/hyperprior-induced-unsupervised","title":"Hyperprior Induced Unsupervised Disentanglement of Latent Representations","arxiv_id":"1809.04497","date":"2018-09-12","proceeding":null,"authors":["Abdul Fatir Ansari","Harold Soh"],"abstract":"We address the problem of unsupervised disentanglement of latent\nrepresentations learnt via deep generative models. In contrast to current\napproaches that operate on the evidence lower bound (ELBO), we argue that\nstatistical independence in the latent space of VAEs can be enforced in a\nprincipled hierarchical Bayesian manner. To this effect, we augment the\nstandard VAE with an inverse-Wishart (IW) prior on the covariance matrix of the\nlatent code. By tuning the IW parameters, we are able to encourage (or\ndiscourage) independence in the learnt latent dimensions. Extensive\nexperimental results on a range of datasets (2DShapes, 3DChairs, 3DFaces and\nCelebA) show our approach to outperform the $\\beta$-VAE and is competitive with\nthe state-of-the-art FactorVAE. Our approach achieves significantly better\ndisentanglement and reconstruction on a new dataset (CorrelatedEllipses) which\nintroduces correlations between the factors of variation.","url_abs":"http://arxiv.org/abs/1809.04497v3","url_pdf":"http://arxiv.org/pdf/1809.04497v3.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":"hyperprior-induced-unsupervised","repo_url":"https://github.com/crslab/CHyVAE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"hyperprior-induced-unsupervised","repo_url":"https://github.com/crslab/correlated-ellipses","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.04497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.04497"}},"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/crslab/correlated-ellipses","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/crslab/CHyVAE","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"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":"90de0586e0ae1e53","entry":"draw_ellipse","repo":"crslab/correlated-ellipses","repo_kind":"listed","path":"synthetic.py","file_url":"https://github.com/crslab/correlated-ellipses/blob/HEAD/synthetic.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":"90de0586e0ae1e53"}},{"code_sha256_prefix":"088915d989f9d403","entry":"latent2image","repo":"crslab/correlated-ellipses","repo_kind":"listed","path":"synthetic.py","file_url":"https://github.com/crslab/correlated-ellipses/blob/HEAD/synthetic.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":"088915d989f9d403"}},{"code_sha256_prefix":"357d01b64500e2d2","entry":"resize_images","repo":"crslab/correlated-ellipses","repo_kind":"listed","path":"synthetic.py","file_url":"https://github.com/crslab/correlated-ellipses/blob/HEAD/synthetic.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":"357d01b64500e2d2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}