{"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/lfme-a-simple-framework-for-learning-from","title":"LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization","arxiv_id":"2410.17020","date":"2024-10-22","proceeding":null,"authors":["Liang Chen","Yong Zhang","Yibing Song","Zhiqiang Shen","Lingqiao Liu"],"abstract":"Domain generalization (DG) methods aim to maintain good performance in an unseen target domain by using training data from multiple source domains. While success on certain occasions are observed, enhancing the baseline across most scenarios remains challenging. This work introduces a simple yet effective framework, dubbed learning from multiple experts (LFME), that aims to make the target model an expert in all source domains to improve DG. Specifically, besides learning the target model used in inference, LFME will also train multiple experts specialized in different domains, whose output probabilities provide professional guidance by simply regularizing the logit of the target model. Delving deep into the framework, we reveal that the introduced logit regularization term implicitly provides effects of enabling the target model to harness more information, and mining hard samples from the experts during training. Extensive experiments on benchmarks from different DG tasks demonstrate that LFME is consistently beneficial to the baseline and can achieve comparable performance to existing arts. Code is available at~\\url{https://github.com/liangchen527/LFME}.","url_abs":"https://arxiv.org/abs/2410.17020v2","url_pdf":"https://arxiv.org/pdf/2410.17020v2.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":"lfme-a-simple-framework-for-learning-from","repo_url":"https://github.com/liangchen527/lfme","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"}],"methods":[{"method_slug":"lfme","method_name":"LFME"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2410.17020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17020"}},"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/liangchen527/LFME","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liangchen527/lfme","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"b9da06d4f527dd6c","entry":"channel_shuffle","repo":"liangchen527/LFME","repo_kind":"official","path":"semantic_segmentation/network/Shufflenet.py","file_url":"https://github.com/liangchen527/LFME/blob/HEAD/semantic_segmentation/network/Shufflenet.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b9da06d4f527dd6c"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"liangchen527/LFME","repo_kind":"official","path":"semantic_segmentation/network/Resnet.py","file_url":"https://github.com/liangchen527/LFME/blob/HEAD/semantic_segmentation/network/Resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"53fac8d8d949e72b","entry":"get_test_records","repo":"liangchen527/LFME","repo_kind":"official","path":"domain_generalization/domainbed/model_selection.py","file_url":"https://github.com/liangchen527/LFME/blob/HEAD/domain_generalization/domainbed/model_selection.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"53fac8d8d949e72b"}},{"code_sha256_prefix":"196cab71d7129d62","entry":"remove_batch_norm_from_resnet","repo":"liangchen527/LFME","repo_kind":"official","path":"domain_generalization/domainbed/networks.py","file_url":"https://github.com/liangchen527/LFME/blob/HEAD/domain_generalization/domainbed/networks.py","link_basis":"plan_row","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":"196cab71d7129d62"}},{"code_sha256_prefix":"d624e152f59e4b06","entry":"Featurizer_OTHMix","repo":"liangchen527/LFME","repo_kind":"official","path":"domain_generalization/domainbed/networks.py","file_url":"https://github.com/liangchen527/LFME/blob/HEAD/domain_generalization/domainbed/networks.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":"d624e152f59e4b06"}},{"code_sha256_prefix":"e38e1b9665be8242","entry":"get_loss_aux","repo":"liangchen527/LFME","repo_kind":"official","path":"semantic_segmentation/loss.py","file_url":"https://github.com/liangchen527/LFME/blob/HEAD/semantic_segmentation/loss.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":"e38e1b9665be8242"}},{"code_sha256_prefix":"db08359f3d18f85c","entry":"make_cov_index_matrix","repo":"liangchen527/LFME","repo_kind":"official","path":"semantic_segmentation/network/cov_settings.py","file_url":"https://github.com/liangchen527/LFME/blob/HEAD/semantic_segmentation/network/cov_settings.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":"db08359f3d18f85c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}