{"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/attend-infer-repeat-fast-scene-understanding","title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","arxiv_id":"1603.08575","date":"2016-03-28","proceeding":"NeurIPS 2016 12","authors":["S. M. Ali Eslami","Nicolas Heess","Theophane Weber","Yuval Tassa","David Szepesvari","Koray Kavukcuoglu","Geoffrey E. Hinton"],"abstract":"We present a framework for efficient inference in structured image models\nthat explicitly reason about objects. We achieve this by performing\nprobabilistic inference using a recurrent neural network that attends to scene\nelements and processes them one at a time. Crucially, the model itself learns\nto choose the appropriate number of inference steps. We use this scheme to\nlearn to perform inference in partially specified 2D models (variable-sized\nvariational auto-encoders) and fully specified 3D models (probabilistic\nrenderers). We show that such models learn to identify multiple objects -\ncounting, locating and classifying the elements of a scene - without any\nsupervision, e.g., decomposing 3D images with various numbers of objects in a\nsingle forward pass of a neural network. We further show that the networks\nproduce accurate inferences when compared to supervised counterparts, and that\ntheir structure leads to improved generalization.","url_abs":"http://arxiv.org/abs/1603.08575v3","url_pdf":"http://arxiv.org/pdf/1603.08575v3.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":"attend-infer-repeat-fast-scene-understanding","repo_url":"https://github.com/stelzner/monet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"attend-infer-repeat-fast-scene-understanding","repo_url":"https://github.com/addtt/attend-infer-repeat-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.08575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.08575"}},"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/stelzner/monet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/addtt/attend-infer-repeat-pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"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":"d8caecc93cf3fde6","entry":"expand_z_where","repo":"addtt/attend-infer-repeat-pytorch","repo_kind":"listed","path":"utils/spatial_transform.py","file_url":"https://github.com/addtt/attend-infer-repeat-pytorch/blob/HEAD/utils/spatial_transform.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":"d8caecc93cf3fde6"}},{"code_sha256_prefix":"fffefdaa5edd6338","entry":"invert_z_where","repo":"addtt/attend-infer-repeat-pytorch","repo_kind":"listed","path":"utils/spatial_transform.py","file_url":"https://github.com/addtt/attend-infer-repeat-pytorch/blob/HEAD/utils/spatial_transform.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":"fffefdaa5edd6338"}},{"code_sha256_prefix":"4cbb4fd7896be1d9","entry":"nograd_param","repo":"addtt/attend-infer-repeat-pytorch","repo_kind":"listed","path":"utils/misc.py","file_url":"https://github.com/addtt/attend-infer-repeat-pytorch/blob/HEAD/utils/misc.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":"4cbb4fd7896be1d9"}},{"code_sha256_prefix":"fc8cbbf53e7b4ae3","entry":"spatial_transformer","repo":"addtt/attend-infer-repeat-pytorch","repo_kind":"listed","path":"utils/spatial_transform.py","file_url":"https://github.com/addtt/attend-infer-repeat-pytorch/blob/HEAD/utils/spatial_transform.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":"fc8cbbf53e7b4ae3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}