{"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/mapper-multimodal-prior-guided-parameter","title":"MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension","arxiv_id":"2409.13609","date":"2024-09-20","proceeding":null,"authors":["Ting Liu","Zunnan Xu","Yue Hu","Liangtao Shi","Zhiqiang Wang","Quanjun Yin"],"abstract":"Referring Expression Comprehension (REC), which aims to ground a local visual region via natural language, is a task that heavily relies on multimodal alignment. Most existing methods utilize powerful pre-trained models to transfer visual/linguistic knowledge by full fine-tuning. However, full fine-tuning the entire backbone not only breaks the rich prior knowledge embedded in the pre-training, but also incurs significant computational costs. Motivated by the recent emergence of Parameter-Efficient Transfer Learning (PETL) methods, we aim to solve the REC task in an effective and efficient manner. Directly applying these PETL methods to the REC task is inappropriate, as they lack the specific-domain abilities for precise local visual perception and visual-language alignment. Therefore, we propose a novel framework of Multimodal Prior-guided Parameter Efficient Tuning, namely MaPPER. Specifically, MaPPER comprises Dynamic Prior Adapters guided by an aligned prior, and Local Convolution Adapters to extract precise local semantics for better visual perception. Moreover, the Prior-Guided Text module is proposed to further utilize the prior for facilitating the cross-modal alignment. Experimental results on three widely-used benchmarks demonstrate that MaPPER achieves the best accuracy compared to the full fine-tuning and other PETL methods with only 1.41% tunable backbone parameters. Our code is available at https://github.com/liuting20/MaPPER.","url_abs":"https://arxiv.org/abs/2409.13609v3","url_pdf":"https://arxiv.org/pdf/2409.13609v3.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":"mapper-multimodal-prior-guided-parameter","repo_url":"https://github.com/liuting20/mapper","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"cross-modal-alignment","task_name":"cross-modal alignment"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.13609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13609"}},"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/liuting20/mapper","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/liuting20/MaPPER","reach":{"status":"ok"}}],"summary":{"ran":2,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":3,"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":9,"samples":[{"code_sha256_prefix":"e0451d070cb0b43e","entry":"build_vl_transformer","repo":"liuting20/MaPPER","repo_kind":"official","path":"models/vl_transformer.py","file_url":"https://github.com/liuting20/MaPPER/blob/HEAD/models/vl_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e0451d070cb0b43e"}},{"code_sha256_prefix":"f4ac915e5456c67f","entry":"crop","repo":"liuting20/MaPPER","repo_kind":"official","path":"datasets/transforms.py","file_url":"https://github.com/liuting20/MaPPER/blob/HEAD/datasets/transforms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f4ac915e5456c67f"}},{"code_sha256_prefix":"e7fcb6d9ac9deaf4","entry":"named_apply","repo":"liuting20/MaPPER","repo_kind":"official","path":"models/backbone/vision_transformer.py","file_url":"https://github.com/liuting20/MaPPER/blob/HEAD/models/backbone/vision_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e7fcb6d9ac9deaf4"}},{"code_sha256_prefix":"694e413f977737ba","entry":"convert_examples_to_features","repo":"liuting20/MaPPER","repo_kind":"official","path":"datasets/data_loader.py","file_url":"https://github.com/liuting20/MaPPER/blob/HEAD/datasets/data_loader.py","link_basis":"harvester_set","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":"694e413f977737ba"}},{"code_sha256_prefix":"b91b981015bbf498","entry":"load","repo":"liuting20/MaPPER","repo_kind":"official","path":"models/clip/clip.py","file_url":"https://github.com/liuting20/MaPPER/blob/HEAD/models/clip/clip.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":"b91b981015bbf498"}},{"code_sha256_prefix":"e4f50d4eeb6144e9","entry":"read_examples","repo":"liuting20/MaPPER","repo_kind":"official","path":"datasets/data_loader.py","file_url":"https://github.com/liuting20/MaPPER/blob/HEAD/datasets/data_loader.py","link_basis":"harvester_set","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":"e4f50d4eeb6144e9"}},{"code_sha256_prefix":"22d10e2294025703","entry":"resize_according_to_long_side","repo":"liuting20/MaPPER","repo_kind":"official","path":"datasets/transforms.py","file_url":"https://github.com/liuting20/MaPPER/blob/HEAD/datasets/transforms.py","link_basis":"harvester_set","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":"22d10e2294025703"}},{"code_sha256_prefix":"553ec6dfb15ff83b","entry":"resize_according_to_short_side","repo":"liuting20/MaPPER","repo_kind":"official","path":"datasets/transforms.py","file_url":"https://github.com/liuting20/MaPPER/blob/HEAD/datasets/transforms.py","link_basis":"harvester_set","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":"553ec6dfb15ff83b"}},{"code_sha256_prefix":"105ac2dc1417db62","entry":"yolo_loss","repo":"liuting20/MaPPER","repo_kind":"official","path":"utils/loss_utils.py","file_url":"https://github.com/liuting20/MaPPER/blob/HEAD/utils/loss_utils.py","link_basis":"harvester_set","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":"105ac2dc1417db62"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}