{"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/meltr-meta-loss-transformer-for-learning-to","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","arxiv_id":"2303.13009","date":"2023-03-23","proceeding":"CVPR 2023 1","authors":["Dohwan Ko","Joonmyung Choi","Hyeong Kyu Choi","Kyoung-Woon On","Byungseok Roh","Hyunwoo J. Kim"],"abstract":"Foundation models have shown outstanding performance and generalization capabilities across domains. Since most studies on foundation models mainly focus on the pretraining phase, a naive strategy to minimize a single task-specific loss is adopted for fine-tuning. However, such fine-tuning methods do not fully leverage other losses that are potentially beneficial for the target task. Therefore, we propose MEta Loss TRansformer (MELTR), a plug-in module that automatically and non-linearly combines various loss functions to aid learning the target task via auxiliary learning. We formulate the auxiliary learning as a bi-level optimization problem and present an efficient optimization algorithm based on Approximate Implicit Differentiation (AID). For evaluation, we apply our framework to various video foundation models (UniVL, Violet and All-in-one), and show significant performance gain on all four downstream tasks: text-to-video retrieval, video question answering, video captioning, and multi-modal sentiment analysis. Our qualitative analyses demonstrate that MELTR adequately `transforms' individual loss functions and `melts' them into an effective unified loss. Code is available at https://github.com/mlvlab/MELTR.","url_abs":"https://arxiv.org/abs/2303.13009v1","url_pdf":"https://arxiv.org/pdf/2303.13009v1.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":"meltr-meta-loss-transformer-for-learning-to","repo_url":"https://github.com/mlvlab/MELTR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"auxiliary-learning","task_name":"Auxiliary Learning"},{"task_slug":"multimodal-sentiment-analysis","task_name":"Multimodal Sentiment Analysis"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"tgif-action","task_name":"TGIF-Action"},{"task_slug":"tgif-frame","task_name":"TGIF-Frame"},{"task_slug":"tgif-transition","task_name":"TGIF-Transition"},{"task_slug":"text-to-video-retrieval","task_name":"Text to Video Retrieval"},{"task_slug":"video-captioning","task_name":"Video Captioning"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multimodal-sentiment-analysis-on-cmu-mosi","task":"Multimodal Sentiment Analysis","dataset":"CMU-MOSI","model":"UniVL + MELTR","rank_in_archive_order":4,"of":12,"metrics":{"Acc-2":"85.3","Corr":"0.789","F1":"85.4","MAE":"0.759"},"uses_additional_data":false},{"leaderboard":"/sota/video-captioning-on-msr-vtt-1","task":"Video Captioning","dataset":"MSR-VTT","model":"UniVL + MELTR","rank_in_archive_order":24,"of":24,"metrics":{"BLEU-4":"44.17","CIDEr":"52.77","METEOR":"29.26","ROUGE-L":"62.35"},"uses_additional_data":false},{"leaderboard":"/sota/video-captioning-on-youcook2","task":"Video Captioning","dataset":"YouCook2","model":"UniVL + MELTR","rank_in_archive_order":2,"of":14,"metrics":{"BLEU-3":"24.12","BLEU-4":"17.92","CIDEr":"1.90","METEOR":"22.56","ROUGE-L":"47.04"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-msr-vtt","task":"Video Retrieval","dataset":"MSR-VTT","model":"All-in-one + MELTR","rank_in_archive_order":15,"of":40,"metrics":{"text-to-video R@1":"38.6","text-to-video R@10":"84.7","text-to-video R@5":"74.4"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-msr-vtt","task":"Video Retrieval","dataset":"MSR-VTT","model":"VIOLET + MELTR","rank_in_archive_order":20,"of":40,"metrics":{"text-to-video Median Rank":"3","text-to-video R@1":"33.6","text-to-video R@10":"77.8","text-to-video R@5":"63.7"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-msr-vtt","task":"Video Retrieval","dataset":"MSR-VTT","model":"UniVL + MELTR","rank_in_archive_order":28,"of":40,"metrics":{"text-to-video Median Rank":"4","text-to-video R@1":"28.5","text-to-video R@10":"67.6","text-to-video R@5":"55.5"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"All-in-one + MELTR","rank_in_archive_order":38,"of":63,"metrics":{"text-to-video R@1":"41.3","text-to-video R@10":"82.5","text-to-video R@5":"73.5"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"VIOLET + MELTR","rank_in_archive_order":46,"of":63,"metrics":{"text-to-video Median Rank":"3","text-to-video R@1":"35.5","text-to-video R@10":"78.4","text-to-video R@5":"67.2"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"UniVL + MELTR","rank_in_archive_order":48,"of":63,"metrics":{"text-to-video Median Rank":"4","text-to-video R@1":"31.1","text-to-video R@10":"68.3","text-to-video R@5":"55.7"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-youcook2","task":"Video Retrieval","dataset":"YouCook2","model":"UniVL + MELTR","rank_in_archive_order":2,"of":16,"metrics":{"text-to-video Median Rank":"3","text-to-video R@1":"33.7","text-to-video R@10":"74.8","text-to-video R@5":"63.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-msvd-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSVD-QA","model":"VIOLET + MELTR","rank_in_archive_order":20,"of":36,"metrics":{"Accuracy":"0.517"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.13009","atlas_url":"https://app.syntology.ai/?focus=2303.13009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13009"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mlvlab/MELTR","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"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":0,"samples":[{"code_sha256_prefix":"a3964b84fb27d6e4","entry":"MELTR","repo":"mlvlab/MELTR","repo_kind":"official","path":"univl/modules/meltr.py","file_url":"https://github.com/mlvlab/MELTR/blob/HEAD/univl/modules/meltr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3964b84fb27d6e4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}