{"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/rethinking-multimodal-learning-from-the","title":"Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability Disproportion","arxiv_id":"2502.20120","date":"2025-02-27","proceeding":null,"authors":["QingYuan Jiang","Longfei Huang","Yang Yang"],"abstract":"Although multimodal learning~(MML) has garnered remarkable progress, the existence of modality imbalance hinders multimodal learning from achieving its expected superiority over unimodal models in practice. To overcome this issue, mainstream multimodal learning methods have placed greater emphasis on balancing the learning process. However, these approaches do not explicitly enhance the classification ability of weaker modalities, leading to limited performance promotion. By designing a sustained boosting algorithm, we propose a novel multimodal learning approach to dynamically balance the classification ability of weak and strong modalities. Concretely, we first propose a sustained boosting algorithm in multimodal learning by simultaneously optimizing the classification and residual errors using a designed configurable classifier module. Then, we propose an adaptive classifier assignment strategy to dynamically facilitate the classification performance of weak modality. To this end, the classification ability of strong and weak modalities is expected to be balanced, thereby mitigating the imbalance issue. Empirical experiments on widely used datasets reveal the superiority of our method through comparison with various state-of-the-art~(SoTA) multimodal learning baselines.","url_abs":"https://arxiv.org/abs/2502.20120v1","url_pdf":"https://arxiv.org/pdf/2502.20120v1.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":[],"tasks":[{"task_slug":"classification-1","task_name":"Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.20120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20120"}},"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/njustkmg/NeurIPS25-AUG","reach":null}],"summary":{"ran":1,"unverified":5},"by_repo_kind":{"found_in_text":{"samples":6,"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":6,"samples":[{"code_sha256_prefix":"164a67939da0282a","entry":"ResNet","repo":"njustkmg/NeurIPS25-AUG","repo_kind":"found_in_text","path":"model/AudioVideo.py","file_url":"https://github.com/njustkmg/NeurIPS25-AUG/blob/HEAD/model/AudioVideo.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":"164a67939da0282a"}},{"code_sha256_prefix":"fb998e5a0b095b6f","entry":"AVGBShareClassifier","repo":"njustkmg/NeurIPS25-AUG","repo_kind":"found_in_text","path":"model/AudioVideo.py","file_url":"https://github.com/njustkmg/NeurIPS25-AUG/blob/HEAD/model/AudioVideo.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":"fb998e5a0b095b6f"}},{"code_sha256_prefix":"9f4f1611fcc53466","entry":"AudioEncoder","repo":"njustkmg/NeurIPS25-AUG","repo_kind":"found_in_text","path":"model/AudioVideo.py","file_url":"https://github.com/njustkmg/NeurIPS25-AUG/blob/HEAD/model/AudioVideo.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":"9f4f1611fcc53466"}},{"code_sha256_prefix":"47db6bdcd582dd32","entry":"VideoEncoder","repo":"njustkmg/NeurIPS25-AUG","repo_kind":"found_in_text","path":"model/AudioVideo.py","file_url":"https://github.com/njustkmg/NeurIPS25-AUG/blob/HEAD/model/AudioVideo.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":"47db6bdcd582dd32"}},{"code_sha256_prefix":"7531d087b1003c42","entry":"_resnet","repo":"njustkmg/NeurIPS25-AUG","repo_kind":"found_in_text","path":"model/AudioVideo.py","file_url":"https://github.com/njustkmg/NeurIPS25-AUG/blob/HEAD/model/AudioVideo.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":"7531d087b1003c42"}},{"code_sha256_prefix":"cccb9fe23a46236a","entry":"resnet18","repo":"njustkmg/NeurIPS25-AUG","repo_kind":"found_in_text","path":"model/AudioVideo.py","file_url":"https://github.com/njustkmg/NeurIPS25-AUG/blob/HEAD/model/AudioVideo.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":"cccb9fe23a46236a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}