{"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/hada-a-graph-based-amalgamation-framework-in","title":"HADA: A Graph-based Amalgamation Framework in Image-text Retrieval","arxiv_id":"2301.04742","date":"2023-01-11","proceeding":null,"authors":["Manh-Duy Nguyen","Binh T. Nguyen","Cathal Gurrin"],"abstract":"Many models have been proposed for vision and language tasks, especially the image-text retrieval task. All state-of-the-art (SOTA) models in this challenge contained hundreds of millions of parameters. They also were pretrained on a large external dataset that has been proven to make a big improvement in overall performance. It is not easy to propose a new model with a novel architecture and intensively train it on a massive dataset with many GPUs to surpass many SOTA models, which are already available to use on the Internet. In this paper, we proposed a compact graph-based framework, named HADA, which can combine pretrained models to produce a better result, rather than building from scratch. First, we created a graph structure in which the nodes were the features extracted from the pretrained models and the edges connecting them. The graph structure was employed to capture and fuse the information from every pretrained model with each other. Then a graph neural network was applied to update the connection between the nodes to get the representative embedding vector for an image and text. Finally, we used the cosine similarity to match images with their relevant texts and vice versa to ensure a low inference time. Our experiments showed that, although HADA contained a tiny number of trainable parameters, it could increase baseline performance by more than 3.6% in terms of evaluation metrics in the Flickr30k dataset. Additionally, the proposed model did not train on any external dataset and did not require many GPUs but only 1 to train due to its small number of parameters. The source code is available at https://github.com/m2man/HADA.","url_abs":"https://arxiv.org/abs/2301.04742v1","url_pdf":"https://arxiv.org/pdf/2301.04742v1.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":"hada-a-graph-based-amalgamation-framework-in","repo_url":"https://github.com/m2man/HADA-LAVIS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"hada-a-graph-based-amalgamation-framework-in","repo_url":"https://github.com/m2man/hada","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"image-text-retrieval","task_name":"Image-text Retrieval"},{"task_slug":"image-to-text-retrieval","task_name":"Image-to-Text Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"mage-to-text-retrieval","task_name":"mage-to-Text Retrieval"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-flickr30k","task":"Image Retrieval","dataset":"Flickr30k","model":"HADA","rank_in_archive_order":3,"of":9,"metrics":{"Recall@1":"81.36","Recall@10":"98.02","Recall@5":"95.94"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-flickr30k","task":"Image Retrieval","dataset":"Flickr30k","model":"ALBEF","rank_in_archive_order":5,"of":9,"metrics":{"Recall@1":"79.76","Recall@10":"97.72","Recall@5":"95.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-flickr30k","task":"Image Retrieval","dataset":"Flickr30k","model":"UNITER","rank_in_archive_order":6,"of":9,"metrics":{"Recall@1":"75.56","Recall@10":"96.76","Recall@5":"94.08"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-mscoco","task":"Image Retrieval","dataset":"MSCOCO","model":"HADA","rank_in_archive_order":1,"of":3,"metrics":{"Recall@1":"58.46","Recall@10":"89.66","Recall@5":"82.85"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-mscoco","task":"Image Retrieval","dataset":"MSCOCO","model":"BLIP","rank_in_archive_order":2,"of":3,"metrics":{"Recall@1":"57.32","Recall@10":"88.92","Recall@5":"81.84"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-mscoco","task":"Image Retrieval","dataset":"MSCOCO","model":"CLIP","rank_in_archive_order":3,"of":3,"metrics":{"Recall@1":"37.02","Recall@10":"71.5","Recall@5":"61.66"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-flickr30k","task":"Image-to-Text Retrieval","dataset":"Flickr30k","model":"ALBEF","rank_in_archive_order":8,"of":11,"metrics":{"Recall@1":"92.6","Recall@10":"99.9","Recall@5":"99.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-flickr30k","task":"Image-to-Text Retrieval","dataset":"Flickr30k","model":"UNITER","rank_in_archive_order":9,"of":11,"metrics":{"Recall@1":"87.3","Recall@10":"99.2","Recall@5":"98"},"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":[{"repo":"m2man/HADA-LAVIS","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"m2man/hada","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7fa848b379c369436823fa28eda5d536d9b20e063b0e2396ada806f5f844502b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}