{"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/generalization-and-robustness-implications-in","title":"Generalization and Robustness Implications in Object-Centric Learning","arxiv_id":"2107.00637","date":"2021-07-01","proceeding":null,"authors":["Andrea Dittadi","Samuele Papa","Michele De Vita","Bernhard Schölkopf","Ole Winther","Francesco Locatello"],"abstract":"The idea behind object-centric representation learning is that natural scenes can better be modeled as compositions of objects and their relations as opposed to distributed representations. This inductive bias can be injected into neural networks to potentially improve systematic generalization and performance of downstream tasks in scenes with multiple objects. In this paper, we train state-of-the-art unsupervised models on five common multi-object datasets and evaluate segmentation metrics and downstream object property prediction. In addition, we study generalization and robustness by investigating the settings where either a single object is out of distribution -- e.g., having an unseen color, texture, or shape -- or global properties of the scene are altered -- e.g., by occlusions, cropping, or increasing the number of objects. From our experimental study, we find object-centric representations to be useful for downstream tasks and generally robust to most distribution shifts affecting objects. However, when the distribution shift affects the input in a less structured manner, robustness in terms of segmentation and downstream task performance may vary significantly across models and distribution shifts.","url_abs":"https://arxiv.org/abs/2107.00637v3","url_pdf":"https://arxiv.org/pdf/2107.00637v3.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":"generalization-and-robustness-implications-in","repo_url":"https://github.com/addtt/object-centric-library","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"object","task_name":"Object"},{"task_slug":"property-prediction","task_name":"Property Prediction"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"systematic-generalization","task_name":"Systematic Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2107.00637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00637"}},"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/addtt/object-centric-library","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"6fd8666dc3ec8735","entry":"extract_state_dicts","repo":"addtt/object-centric-library","repo_kind":"official","path":"models/base_trainer.py","file_url":"https://github.com/addtt/object-centric-library/blob/HEAD/models/base_trainer.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":"6fd8666dc3ec8735"}},{"code_sha256_prefix":"9c66730718cdc5ce","entry":"get_activation_module","repo":"addtt/object-centric-library","repo_kind":"official","path":"models/nn_utils.py","file_url":"https://github.com/addtt/object-centric-library/blob/HEAD/models/nn_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":"9c66730718cdc5ce"}},{"code_sha256_prefix":"0ae23ca88ab50cab","entry":"get_conv_output_shape","repo":"addtt/object-centric-library","repo_kind":"official","path":"models/nn_utils.py","file_url":"https://github.com/addtt/object-centric-library/blob/HEAD/models/nn_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":"0ae23ca88ab50cab"}},{"code_sha256_prefix":"a8f56dabf6dfb31e","entry":"linear_warmup_exp_decay","repo":"addtt/object-centric-library","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/addtt/object-centric-library/blob/HEAD/models/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":"a8f56dabf6dfb31e"}},{"code_sha256_prefix":"091367aadde66f66","entry":"make_simple_model","repo":"addtt/object-centric-library","repo_kind":"official","path":"evaluation/downstream_models.py","file_url":"https://github.com/addtt/object-centric-library/blob/HEAD/evaluation/downstream_models.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":"091367aadde66f66"}},{"code_sha256_prefix":"4dadf6e32dd339c5","entry":"summary_num_params","repo":"addtt/object-centric-library","repo_kind":"official","path":"models/nn_utils.py","file_url":"https://github.com/addtt/object-centric-library/blob/HEAD/models/nn_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":"4dadf6e32dd339c5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}