{"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/m2df-multi-grained-multi-curriculum-denoising","title":"M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis","arxiv_id":"2310.14605","date":"2023-10-23","proceeding":null,"authors":["Fei Zhao","Chunhui Li","Zhen Wu","Yawen Ouyang","Jianbing Zhang","Xinyu Dai"],"abstract":"Multimodal Aspect-based Sentiment Analysis (MABSA) is a fine-grained Sentiment Analysis task, which has attracted growing research interests recently. Existing work mainly utilizes image information to improve the performance of MABSA task. However, most of the studies overestimate the importance of images since there are many noise images unrelated to the text in the dataset, which will have a negative impact on model learning. Although some work attempts to filter low-quality noise images by setting thresholds, relying on thresholds will inevitably filter out a lot of useful image information. Therefore, in this work, we focus on whether the negative impact of noisy images can be reduced without modifying the data. To achieve this goal, we borrow the idea of Curriculum Learning and propose a Multi-grained Multi-curriculum Denoising Framework (M2DF), which can achieve denoising by adjusting the order of training data. Extensive experimental results show that our framework consistently outperforms state-of-the-art work on three sub-tasks of MABSA.","url_abs":"https://arxiv.org/abs/2310.14605v1","url_pdf":"https://arxiv.org/pdf/2310.14605v1.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":"m2df-multi-grained-multi-curriculum-denoising","repo_url":"https://github.com/grandchicken/m2df","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"aspect-based-sentiment-analysis-1","task_name":"Aspect-Based Sentiment Analysis"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.14605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14605"}},"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/grandchicken/M2DF","reach":null}],"summary":{"ran":1,"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"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":"5b5a95d761761b17","entry":"ImageEmbedding","repo":"grandchicken/M2DF","repo_kind":"official","path":"src/model/modules.py","file_url":"https://github.com/grandchicken/M2DF/blob/HEAD/src/model/modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5b5a95d761761b17"}},{"code_sha256_prefix":"874a42377fa0659f","entry":"invert_mask","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"874a42377fa0659f"}},{"code_sha256_prefix":"072bfd4ade0d9d34","entry":"MultiModalBartConfig","repo":"grandchicken/M2DF","repo_kind":"official","path":"src/model/modules.py","file_url":"https://github.com/grandchicken/M2DF/blob/HEAD/src/model/modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"072bfd4ade0d9d34"}},{"code_sha256_prefix":"d4d6de5f0e36d206","entry":"MultiModalBartEncoder","repo":"grandchicken/M2DF","repo_kind":"official","path":"src/model/modules.py","file_url":"https://github.com/grandchicken/M2DF/blob/HEAD/src/model/modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d4d6de5f0e36d206"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}