{"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":"/method/albef","slug":"albef","name":"ALBEF","full_name":"ALBEF","full_name_withheld":false,"description_markdown":"ALBEF introduces a contrastive loss to align the image and text representations before fusing them through cross-modal attention. This enables more grounded vision and language representation learning. ALBEF also doesn't require bounding box annotations. The model consists of an image encode, a text encoder, and a multimodal encoder. The image-text contrastive loss helps to align the unimodal representations of an image-text pair before fusion. The image-text matching loss and a masked language modeling loss are applied to learn multimodal interactions between image and text. In addition, momentum distillation is used to generate pseudo-targets. This improves learning with noisy data.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","paper":"/paper/align-before-fuse-vision-and-language","first_author":"Junnan Li","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/align-before-fuse-vision-and-language"},"source":{"url":"https://arxiv.org/abs/2107.07651v2","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Vision and Language Pre-Trained Models","url":"/methods/category/vision-and-language-pre-trained-models","pwc_aliases":[]}],"n_papers_tagged":17,"archive_num_papers":17,"papers_newest_first":[{"paper":null,"slug":"barking-up-the-syntactic-tree-enhancing-vlm","title":"Barking Up The Syntactic Tree: Enhancing VLM Training with Syntactic Losses","date":"2024-12-11","arxiv_id":"2412.08110","n_code_links":0,"syntology":null},{"paper":"/paper/nearest-neighbor-normalization-improves","slug":"nearest-neighbor-normalization-improves","title":"Nearest Neighbor Normalization Improves Multimodal Retrieval","date":"2024-10-31","arxiv_id":"2410.24114","n_code_links":1,"syntology":null},{"paper":null,"slug":"q-groundcam-quantifying-grounding-in-vision","title":"Q-GroundCAM: Quantifying Grounding in Vision Language Models via GradCAM","date":"2024-04-29","arxiv_id":"2404.19128","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-from-models-and-data-for-visual","title":"Learning from Synthetic Data for Visual Grounding","date":"2024-03-20","arxiv_id":"2403.13804","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-adversarial-transferability-of","title":"Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction","date":"2024-03-16","arxiv_id":"2403.10883","n_code_links":0,"syntology":null},{"paper":null,"slug":"luojiahog-a-hierarchy-oriented-geo-aware","title":"LuoJiaHOG: A Hierarchy Oriented Geo-aware Image Caption Dataset for Remote Sensing Image-Text Retrival","date":"2024-03-16","arxiv_id":"2403.10887","n_code_links":0,"syntology":null},{"paper":"/paper/set-level-guidance-attack-boosting","slug":"set-level-guidance-attack-boosting","title":"Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models","date":"2023-07-26","arxiv_id":"2307.14061","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":2,"n_instrument":7,"unverified":3,"pointer_only":0,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Zoky-2020/Set-level_Guidance_Attack"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/rasa-relation-and-sensitivity-aware","slug":"rasa-relation-and-sensitivity-aware","title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search","date":"2023-05-23","arxiv_id":"2305.13653","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":1,"n_instrument":4,"unverified":2,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["flame-chasers/rasa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/multimodal-bias-introducing-a-framework-for","slug":"multimodal-bias-introducing-a-framework-for","title":"MultiModal Bias: Introducing a Framework for Stereotypical Bias Assessment beyond Gender and Race in Vision Language Models","date":"2023-03-16","arxiv_id":"2303.12734","n_code_links":1,"syntology":null},{"paper":"/paper/is-multi-modal-vision-supervision-beneficial","slug":"is-multi-modal-vision-supervision-beneficial","title":"Is Multimodal Vision Supervision Beneficial to Language?","date":"2023-02-10","arxiv_id":"2302.05016","n_code_links":1,"syntology":null},{"paper":"/paper/mm-shap-a-performance-agnostic-metric-for","slug":"mm-shap-a-performance-agnostic-metric-for","title":"MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks","date":"2022-12-15","arxiv_id":"2212.08158","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["heidelberg-nlp/mm-shap"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"leveraging-per-image-token-consistency-for","title":"Leveraging per Image-Token Consistency for Vision-Language Pre-training","date":"2022-11-20","arxiv_id":"2211.15398","n_code_links":0,"syntology":null},{"paper":"/paper/grit-vlp-grouped-mini-batch-sampling-for","slug":"grit-vlp-grouped-mini-batch-sampling-for","title":"GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training","date":"2022-08-08","arxiv_id":"2208.04060","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jaeseokbyun/grit-vlp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/chiqa-a-large-scale-image-based-real-world","slug":"chiqa-a-large-scale-image-based-real-world","title":"ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding","date":"2022-08-05","arxiv_id":"2208.03030","n_code_links":1,"syntology":null},{"paper":"/paper/vl-checklist-evaluating-pre-trained-vision","slug":"vl-checklist-evaluating-pre-trained-vision","title":"VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations","date":"2022-07-01","arxiv_id":"2207.00221","n_code_links":1,"syntology":null},{"paper":"/paper/mixgen-a-new-multi-modal-data-augmentation","slug":"mixgen-a-new-multi-modal-data-augmentation","title":"MixGen: A New Multi-Modal Data Augmentation","date":"2022-06-16","arxiv_id":"2206.08358","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["amazon-research/mix-generation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/align-before-fuse-vision-and-language","slug":"align-before-fuse-vision-and-language","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","date":"2021-07-16","arxiv_id":"2107.07651","n_code_links":6,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["salesforce/lavis"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"papers_shown":17,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":17,"with_a_code_link":11,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":17,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/method/albef/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/albef/papers/ran/1","json":"/method/albef/papers/ran/1.json","rows":5}],"tasks":[{"task":"/task/image-text-retrieval","name":"Image-text Retrieval","papers":7},{"task":"/task/retrieval","name":"Retrieval","papers":7},{"task":"/task/text-retrieval","name":"Text Retrieval","papers":7},{"task":"/task/question-answering","name":"Question Answering","papers":5},{"task":"/task/visual-question-answering-1","name":"Visual Question Answering","papers":5},{"task":"/task/visual-question-answering","name":"Visual Question Answering (VQA)","papers":4},{"task":"/task/image-retrieval","name":"Image Retrieval","papers":3},{"task":"/task/language-modelling","name":"Language Modelling","papers":3},{"task":"/task/visual-grounding","name":"Visual Grounding","papers":3},{"task":"/task/cross-modal-retrieval","name":"Cross-Modal Retrieval","papers":2},{"task":"/task/image-text-matching","name":"Image-text matching","papers":2},{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/masked-language-modeling","name":"Masked Language Modeling","papers":2},{"task":"/task/representation-learning","name":"Representation Learning","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/visual-reasoning","name":"Visual Reasoning","papers":2},{"task":"/task/adversarial-robustness","name":"Adversarial Robustness","papers":1},{"task":"/task/caption-generation","name":"Caption Generation","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/grounded-language-learning","name":"Grounded language learning","papers":1}],"tasks_shown":20,"n_tasks":38,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":6},{"year":"2023","papers":4},{"year":"2024","papers":6}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/albef"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=ALBEF","read_at":"2026-10-05T00:51:48+00:00","query":"ALBEF","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"2107.07651","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'ALBEF' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"30dfc6b6bf02b1daf6257e327ade2e8c191aacb6b4d527dd5700924f9756645a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}