{"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/not-just-object-but-state-compositional","title":"Not Just Object, But State: Compositional Incremental Learning without Forgetting","arxiv_id":"2411.01739","date":"2024-11-04","proceeding":null,"authors":["Yanyi Zhang","Binglin Qiu","Qi Jia","Yu Liu","Ran He"],"abstract":"Most incremental learners excessively prioritize coarse classes of objects while neglecting various kinds of states (e.g. color and material) attached to the objects. As a result, they are limited in the ability to reason fine-grained compositionality of state-object pairs. To remedy this limitation, we propose a novel task called Compositional Incremental Learning (composition-IL), enabling the model to recognize state-object compositions as a whole in an incremental learning fashion. Since the lack of suitable benchmarks, we re-organize two existing datasets and make them tailored for composition-IL. Then, we propose a prompt-based Composition Incremental Learner (CompILer), to overcome the ambiguous composition boundary problem which challenges composition-IL largely. Specifically, we exploit multi-pool prompt learning, which is regularized by inter-pool prompt discrepancy and intra-pool prompt diversity. Besides, we devise object-injected state prompting by using object prompts to guide the selection of state prompts. Furthermore, we fuse the selected prompts by a generalized-mean strategy, to eliminate irrelevant information learned in the prompts. Extensive experiments on two datasets exhibit state-of-the-art performance achieved by CompILer.","url_abs":"https://arxiv.org/abs/2411.01739v3","url_pdf":"https://arxiv.org/pdf/2411.01739v3.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":"not-just-object-but-state-compositional","repo_url":"https://github.com/Yanyi-Zhang/CompILer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"prompt-learning","task_name":"Prompt Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.01739","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.01739"}},"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/Yanyi-Zhang/CompILer","reach":null}],"summary":{"ran":2,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"c589fd1d598b4faf","entry":"GeM","repo":"Yanyi-Zhang/CompILer","repo_kind":"official","path":"prompt.py","file_url":"https://github.com/Yanyi-Zhang/CompILer/blob/HEAD/prompt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c589fd1d598b4faf"}},{"code_sha256_prefix":"83b748f7a2039624","entry":"Prompt","repo":"Yanyi-Zhang/CompILer","repo_kind":"official","path":"prompt.py","file_url":"https://github.com/Yanyi-Zhang/CompILer/blob/HEAD/prompt.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":"83b748f7a2039624"}},{"code_sha256_prefix":"d924e2d01046619b","entry":"ddl_loss","repo":"Yanyi-Zhang/CompILer","repo_kind":"official","path":"prompt.py","file_url":"https://github.com/Yanyi-Zhang/CompILer/blob/HEAD/prompt.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d924e2d01046619b"}},{"code_sha256_prefix":"70ec748890fe3204","entry":"ortho_penalty","repo":"Yanyi-Zhang/CompILer","repo_kind":"official","path":"prompt.py","file_url":"https://github.com/Yanyi-Zhang/CompILer/blob/HEAD/prompt.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"70ec748890fe3204"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}