{"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/vision-transformers-are-parameter-efficient","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","arxiv_id":"2212.07983","date":"2022-12-15","proceeding":"CVPR 2023 1","authors":["Yan-Bo Lin","Yi-Lin Sung","Jie Lei","Mohit Bansal","Gedas Bertasius"],"abstract":"Vision transformers (ViTs) have achieved impressive results on various computer vision tasks in the last several years. In this work, we study the capability of frozen ViTs, pretrained only on visual data, to generalize to audio-visual data without finetuning any of its original parameters. To do so, we propose a latent audio-visual hybrid (LAVISH) adapter that adapts pretrained ViTs to audio-visual tasks by injecting a small number of trainable parameters into every layer of a frozen ViT. To efficiently fuse visual and audio cues, our LAVISH adapter uses a small set of latent tokens, which form an attention bottleneck, thus, eliminating the quadratic cost of standard cross-attention. Compared to the existing modality-specific audio-visual methods, our approach achieves competitive or even better performance on various audio-visual tasks while using fewer tunable parameters and without relying on costly audio pretraining or external audio encoders. Our code is available at https://genjib.github.io/project_page/LAVISH/","url_abs":"https://arxiv.org/abs/2212.07983v2","url_pdf":"https://arxiv.org/pdf/2212.07983v2.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":"vision-transformers-are-parameter-efficient","repo_url":"https://github.com/GenjiB/LAVISH","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"audio-visual-question-answering-music-avqa-v2","task_name":"AUDIO-VISUAL QUESTION ANSWERING (MUSIC-AVQA-v2.0)"},{"task_slug":"audio-visual-question-answering","task_name":"Audio-visual Question Answering"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-visual-question-answering-music-avqa-v2","task":"AUDIO-VISUAL QUESTION ANSWERING (MUSIC-AVQA-v2.0)","dataset":"MUSIC-AVQA v2.0","model":"LAVISH","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"73.18"},"uses_additional_data":false},{"leaderboard":"/sota/audio-visual-question-answering-on-music-avqa","task":"Audio-visual Question Answering","dataset":"MUSIC-AVQA","model":"LAVISH","rank_in_archive_order":5,"of":6,"metrics":{"Acc":"77.08"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.07983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.07983"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/GenjiB/LAVISH","reach":null}],"summary":{"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"4eb3193bc43cfa55","entry":"test","repo":"GenjiB/LAVISH","repo_kind":"official","path":"AVQA/grounding_gen/main_grd_gen.py","file_url":"https://github.com/GenjiB/LAVISH/blob/HEAD/AVQA/grounding_gen/main_grd_gen.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4eb3193bc43cfa55"}},{"code_sha256_prefix":"ad990ebf7a5dc52a","entry":"eval","repo":"GenjiB/LAVISH","repo_kind":"official","path":"AVE/main_trans.py","file_url":"https://github.com/GenjiB/LAVISH/blob/HEAD/AVE/main_trans.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":"ad990ebf7a5dc52a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}