{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/less-is-more-linear-layers-on-clip-features","title":"Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model","arxiv_id":"2206.05281","date":"2022-06-10","proceeding":null,"authors":["Fabian Deuser","Konrad Habel","Philipp J. Rösch","Norbert Oswald"],"abstract":"Current architectures for multi-modality tasks such as visual question answering suffer from their high complexity. As a result, these architectures are difficult to train and require high computational resources. To address these problems we present a CLIP-based architecture that does not require any fine-tuning of the feature extractors. A simple linear classifier is used on the concatenated features of the image and text encoder. During training an auxiliary loss is added which operates on the answer types. The resulting classification is then used as an attention gate on the answer class selection. On the VizWiz 2022 Visual Question Answering Challenge we achieve 60.15 % accuracy on Task 1: Predict Answer to a Visual Question and AP score of 83.78 % on Task 2: Predict Answerability of a Visual Question.","url_abs":"https://arxiv.org/abs/2206.05281v1","url_pdf":"https://arxiv.org/pdf/2206.05281v1.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":"question-answering","task_name":"Question Answering"},{"task_slug":"task-2","task_name":"Task 2"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"auxiliary-classifier","method_name":"Auxiliary Classifier"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"linear-layer","method_name":"Linear Layer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-vizwiz-2020","task":"Visual Question Answering (VQA)","dataset":"VizWiz 2020 Answerability","model":"CLIP-Ensemble","rank_in_archive_order":1,"of":6,"metrics":{"average_precision":"84.13"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vizwiz-2020","task":"Visual Question Answering (VQA)","dataset":"VizWiz 2020 Answerability","model":"CLIP-Single","rank_in_archive_order":2,"of":6,"metrics":{"average_precision":"82.86"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vizwiz-2020-vqa","task":"Visual Question Answering (VQA)","dataset":"VizWiz 2020 VQA","model":"CLIP-Ensemble","rank_in_archive_order":2,"of":16,"metrics":{"overall":"61.64"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vizwiz-2020-vqa","task":"Visual Question Answering (VQA)","dataset":"VizWiz 2020 VQA","model":"CLIP-Single","rank_in_archive_order":3,"of":16,"metrics":{"overall":"60.66"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"9dfc680575b646754449e6f6e499b2c7d686e36094b0d8978a0929035a0ff567","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}