{"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/unsupervised-learning-of-compositional-energy","title":"Unsupervised Learning of Compositional Energy Concepts","arxiv_id":"2111.03042","date":"2021-11-04","proceeding":"NeurIPS 2021 12","authors":["Yilun Du","Shuang Li","Yash Sharma","Joshua B. Tenenbaum","Igor Mordatch"],"abstract":"Humans are able to rapidly understand scenes by utilizing concepts extracted from prior experience. Such concepts are diverse, and include global scene descriptors, such as the weather or lighting, as well as local scene descriptors, such as the color or size of a particular object. So far, unsupervised discovery of concepts has focused on either modeling the global scene-level or the local object-level factors of variation, but not both. In this work, we propose COMET, which discovers and represents concepts as separate energy functions, enabling us to represent both global concepts as well as objects under a unified framework. COMET discovers energy functions through recomposing the input image, which we find captures independent factors without additional supervision. Sample generation in COMET is formulated as an optimization process on underlying energy functions, enabling us to generate images with permuted and composed concepts. Finally, discovered visual concepts in COMET generalize well, enabling us to compose concepts between separate modalities of images as well as with other concepts discovered by a separate instance of COMET trained on a different dataset. Code and data available at https://energy-based-model.github.io/comet/.","url_abs":"https://arxiv.org/abs/2111.03042v1","url_pdf":"https://arxiv.org/pdf/2111.03042v1.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":"unsupervised-learning-of-compositional-energy","repo_url":"https://github.com/yilundu/comet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"unsupervised-image-decomposition","task_name":"Unsupervised Image Decomposition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2111.03042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03042"}},"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/yilundu/comet","reach":null}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"ed416d7c3f68dde1","entry":"BroadcastConvDecoder","repo":"yilundu/comet","repo_kind":"official","path":"models.py","file_url":"https://github.com/yilundu/comet/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ed416d7c3f68dde1"}},{"code_sha256_prefix":"75e1e7c55b1d9b8e","entry":"CondResBlock","repo":"yilundu/comet","repo_kind":"official","path":"models.py","file_url":"https://github.com/yilundu/comet/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"75e1e7c55b1d9b8e"}},{"code_sha256_prefix":"337c366de3c28acd","entry":"CondResBlockNoLatent","repo":"yilundu/comet","repo_kind":"official","path":"models.py","file_url":"https://github.com/yilundu/comet/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"337c366de3c28acd"}},{"code_sha256_prefix":"15c654593131627f","entry":"Downsample","repo":"yilundu/comet","repo_kind":"official","path":"models.py","file_url":"https://github.com/yilundu/comet/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"15c654593131627f"}},{"code_sha256_prefix":"54bab9e82af71006","entry":"LatentEBM128","repo":"yilundu/comet","repo_kind":"official","path":"models.py","file_url":"https://github.com/yilundu/comet/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"54bab9e82af71006"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}