{"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/monet-unsupervised-scene-decomposition-and","title":"MONet: Unsupervised Scene Decomposition and Representation","arxiv_id":"1901.11390","date":"2019-01-22","proceeding":null,"authors":["Christopher P. Burgess","Loic Matthey","Nicholas Watters","Rishabh Kabra","Irina Higgins","Matt Botvinick","Alexander Lerchner"],"abstract":"The ability to decompose scenes in terms of abstract building blocks is\ncrucial for general intelligence. Where those basic building blocks share\nmeaningful properties, interactions and other regularities across scenes, such\ndecompositions can simplify reasoning and facilitate imagination of novel\nscenarios. In particular, representing perceptual observations in terms of\nentities should improve data efficiency and transfer performance on a wide\nrange of tasks. Thus we need models capable of discovering useful\ndecompositions of scenes by identifying units with such regularities and\nrepresenting them in a common format. To address this problem, we have\ndeveloped the Multi-Object Network (MONet). In this model, a VAE is trained\nend-to-end together with a recurrent attention network -- in a purely\nunsupervised manner -- to provide attention masks around, and reconstructions\nof, regions of images. We show that this model is capable of learning to\ndecompose and represent challenging 3D scenes into semantically meaningful\ncomponents, such as objects and background elements.","url_abs":"http://arxiv.org/abs/1901.11390v1","url_pdf":"http://arxiv.org/pdf/1901.11390v1.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":"monet-unsupervised-scene-decomposition-and","repo_url":"https://github.com/JohannesTheo/multi_object_datasets_torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"monet-unsupervised-scene-decomposition-and","repo_url":"https://github.com/Michedev/MONet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"monet-unsupervised-scene-decomposition-and","repo_url":"https://github.com/baudm/MONet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"monet-unsupervised-scene-decomposition-and","repo_url":"https://github.com/deepmind/multi_object_datasets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"monet-unsupervised-scene-decomposition-and","repo_url":"https://github.com/stelzner/monet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object-discovery","task_name":"Object Discovery"},{"task_slug":"unsupervised-object-segmentation","task_name":"Unsupervised Object Segmentation"}],"methods":[{"method_slug":"sbd","method_name":"Spatial Broadcast Decoder"}],"datasets_introduced":[{"slug":"multi-dsprites","name":"Multi-dSprites","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1901.11390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.11390"}},"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/deepmind/multi_object_datasets","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baudm/MONet-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JohannesTheo/multi_object_datasets_torch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stelzner/monet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Michedev/MONet-pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"listed":{"samples":7,"ran":1,"repositories":3}},"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":"6197a19b88fb1aed","entry":"double_conv","repo":"stelzner/monet","repo_kind":"listed","path":"model.py","file_url":"https://github.com/stelzner/monet/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6197a19b88fb1aed"}},{"code_sha256_prefix":"4278b4b72fbcd18d","entry":"adjusted_rand_index","repo":"JohannesTheo/multi_object_datasets_torch","repo_kind":"listed","path":"segmentation_metrics.py","file_url":"https://github.com/JohannesTheo/multi_object_datasets_torch/blob/HEAD/segmentation_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4278b4b72fbcd18d"}},{"code_sha256_prefix":"ba8e0e813053eb4b","entry":"calc_output_shape_conv","repo":"Michedev/MONet-pytorch","repo_kind":"listed","path":"monet_pytorch/nn_utils.py","file_url":"https://github.com/Michedev/MONet-pytorch/blob/HEAD/monet_pytorch/nn_utils.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":"ba8e0e813053eb4b"}},{"code_sha256_prefix":"4628ccf7333c9464","entry":"flatten_and_one_hot","repo":"JohannesTheo/multi_object_datasets_torch","repo_kind":"listed","path":"segmentation_metrics.py","file_url":"https://github.com/JohannesTheo/multi_object_datasets_torch/blob/HEAD/segmentation_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4628ccf7333c9464"}},{"code_sha256_prefix":"b2e2bd230042f9d9","entry":"get_activation_module","repo":"Michedev/MONet-pytorch","repo_kind":"listed","path":"monet_pytorch/nn_utils.py","file_url":"https://github.com/Michedev/MONet-pytorch/blob/HEAD/monet_pytorch/nn_utils.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":"b2e2bd230042f9d9"}},{"code_sha256_prefix":"b0b63ba660be532e","entry":"norm_gradient","repo":"Michedev/MONet-pytorch","repo_kind":"listed","path":"monet_pytorch/nn_utils.py","file_url":"https://github.com/Michedev/MONet-pytorch/blob/HEAD/monet_pytorch/nn_utils.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":"b0b63ba660be532e"}},{"code_sha256_prefix":"f293405163eeb8e0","entry":"random_predictions_like","repo":"JohannesTheo/multi_object_datasets_torch","repo_kind":"listed","path":"segmentation_metrics.py","file_url":"https://github.com/JohannesTheo/multi_object_datasets_torch/blob/HEAD/segmentation_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f293405163eeb8e0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}