{"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/efficient-iterative-amortized-inference-for","title":"Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations","arxiv_id":"2106.03630","date":"2021-06-07","proceeding":null,"authors":["Patrick Emami","Pan He","Sanjay Ranka","Anand Rangarajan"],"abstract":"Unsupervised multi-object representation learning depends on inductive biases to guide the discovery of object-centric representations that generalize. However, we observe that methods for learning these representations are either impractical due to long training times and large memory consumption or forego key inductive biases. In this work, we introduce EfficientMORL, an efficient framework for the unsupervised learning of object-centric representations. We show that optimization challenges caused by requiring both symmetry and disentanglement can in fact be addressed by high-cost iterative amortized inference by designing the framework to minimize its dependence on it. We take a two-stage approach to inference: first, a hierarchical variational autoencoder extracts symmetric and disentangled representations through bottom-up inference, and second, a lightweight network refines the representations with top-down feedback. The number of refinement steps taken during training is reduced following a curriculum, so that at test time with zero steps the model achieves 99.1% of the refined decomposition performance. We demonstrate strong object decomposition and disentanglement on the standard multi-object benchmark while achieving nearly an order of magnitude faster training and test time inference over the previous state-of-the-art model.","url_abs":"https://arxiv.org/abs/2106.03630v1","url_pdf":"https://arxiv.org/pdf/2106.03630v1.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":"efficient-iterative-amortized-inference-for","repo_url":"https://github.com/pemami4911/EfficientMORL","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":"object","task_name":"Object"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.03630","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03630"}},"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":"deterministic:regex_extraction","url":"https://github.com/pemami4911/EfficientMORL","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":2,"unverified":7},"by_repo_kind":{"official":{"samples":9,"ran":2,"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":"9036466b82f32c46","entry":"disentanglement","repo":"pemami4911/EfficientMORL","repo_kind":"official","path":"lib/dci.py","file_url":"https://github.com/pemami4911/EfficientMORL/blob/HEAD/lib/dci.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9036466b82f32c46"}},{"code_sha256_prefix":"4549dd9ced62ede6","entry":"disentanglement_per_code","repo":"pemami4911/EfficientMORL","repo_kind":"official","path":"lib/dci.py","file_url":"https://github.com/pemami4911/EfficientMORL/blob/HEAD/lib/dci.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4549dd9ced62ede6"}},{"code_sha256_prefix":"541dc5b4ae07fd63","entry":"adjusted_rand_index","repo":"pemami4911/EfficientMORL","repo_kind":"official","path":"lib/metrics.py","file_url":"https://github.com/pemami4911/EfficientMORL/blob/HEAD/lib/metrics.py","link_basis":"first_harvest_node","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":"541dc5b4ae07fd63"}},{"code_sha256_prefix":"805f21804621c710","entry":"compute_importance","repo":"pemami4911/EfficientMORL","repo_kind":"official","path":"lib/dci.py","file_url":"https://github.com/pemami4911/EfficientMORL/blob/HEAD/lib/dci.py","link_basis":"first_harvest_node","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":"805f21804621c710"}},{"code_sha256_prefix":"20d9d7494743e9bc","entry":"matching_iou","repo":"pemami4911/EfficientMORL","repo_kind":"official","path":"lib/metrics.py","file_url":"https://github.com/pemami4911/EfficientMORL/blob/HEAD/lib/metrics.py","link_basis":"first_harvest_node","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":"20d9d7494743e9bc"}},{"code_sha256_prefix":"59431095f0631f85","entry":"mvn","repo":"pemami4911/EfficientMORL","repo_kind":"official","path":"lib/utils.py","file_url":"https://github.com/pemami4911/EfficientMORL/blob/HEAD/lib/utils.py","link_basis":"first_harvest_node","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":"59431095f0631f85"}},{"code_sha256_prefix":"1e58c4d04b02b286","entry":"pixel_mse","repo":"pemami4911/EfficientMORL","repo_kind":"official","path":"lib/metrics.py","file_url":"https://github.com/pemami4911/EfficientMORL/blob/HEAD/lib/metrics.py","link_basis":"first_harvest_node","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":"1e58c4d04b02b286"}},{"code_sha256_prefix":"dbbbca9a6ee4050e","entry":"std_mvn","repo":"pemami4911/EfficientMORL","repo_kind":"official","path":"lib/utils.py","file_url":"https://github.com/pemami4911/EfficientMORL/blob/HEAD/lib/utils.py","link_basis":"first_harvest_node","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":"dbbbca9a6ee4050e"}},{"code_sha256_prefix":"f063d80ee3c977d0","entry":"truncated_normal_initializer","repo":"pemami4911/EfficientMORL","repo_kind":"official","path":"lib/utils.py","file_url":"https://github.com/pemami4911/EfficientMORL/blob/HEAD/lib/utils.py","link_basis":"first_harvest_node","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":"f063d80ee3c977d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}