{"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/bridging-vision-and-language-encoders","title":"Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation","arxiv_id":"2307.11545","date":"2023-07-21","proceeding":"ICCV 2023 1","authors":["Zunnan Xu","Zhihong Chen","Yong Zhang","Yibing Song","Xiang Wan","Guanbin Li"],"abstract":"Parameter Efficient Tuning (PET) has gained attention for reducing the number of parameters while maintaining performance and providing better hardware resource savings, but few studies investigate dense prediction tasks and interaction between modalities. In this paper, we do an investigation of efficient tuning problems on referring image segmentation. We propose a novel adapter called Bridger to facilitate cross-modal information exchange and inject task-specific information into the pre-trained model. We also design a lightweight decoder for image segmentation. Our approach achieves comparable or superior performance with only 1.61\\% to 3.38\\% backbone parameter updates, evaluated on challenging benchmarks. The code is available at \\url{https://github.com/kkakkkka/ETRIS}.","url_abs":"https://arxiv.org/abs/2307.11545v1","url_pdf":"https://arxiv.org/pdf/2307.11545v1.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":"bridging-vision-and-language-encoders","repo_url":"https://github.com/kkakkkka/etris","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-6","task":"Referring Expression Segmentation","dataset":"RefCOCO","model":"ETRIS","rank_in_archive_order":4,"of":4,"metrics":{"IoU":"71.06"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco","task":"Referring Expression Segmentation","dataset":"RefCoCo val","model":"ETRIS","rank_in_archive_order":23,"of":37,"metrics":{"Overall IoU":"71.06"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.11545","atlas_url":"https://app.syntology.ai/?focus=2307.11545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.11545"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/kkakkkka/etris","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/kkakkkka/ETRIS","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_draft_wrong":5,"unverified":8},"by_repo_kind":{"official":{"samples":16,"ran":8,"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":0,"samples":[{"code_sha256_prefix":"dcafe7ec4c3e2899","entry":"Interactor","repo":"kkakkkka/ETRIS","repo_kind":"official","path":"model/bridger.py","file_url":"https://github.com/kkakkkka/ETRIS/blob/HEAD/model/bridger.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dcafe7ec4c3e2899"}},{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"kkakkkka/etris","repo_kind":"official","path":"utils/simple_tokenizer.py","file_url":"https://github.com/kkakkkka/etris/blob/HEAD/utils/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"dbfe3357dc25ca5f","entry":"conv_layer","repo":"kkakkkka/etris","repo_kind":"official","path":"model/layers.py","file_url":"https://github.com/kkakkkka/etris/blob/HEAD/model/layers.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dbfe3357dc25ca5f"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"kkakkkka/etris","repo_kind":"official","path":"utils/simple_tokenizer.py","file_url":"https://github.com/kkakkkka/etris/blob/HEAD/utils/simple_tokenizer.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"539cbfa1328eb51b","entry":"init_random_seed","repo":"kkakkkka/etris","repo_kind":"official","path":"utils/misc.py","file_url":"https://github.com/kkakkkka/etris/blob/HEAD/utils/misc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"539cbfa1328eb51b"}},{"code_sha256_prefix":"89f9fd49ddec76ba","entry":"linear_layer","repo":"kkakkkka/etris","repo_kind":"official","path":"model/layers.py","file_url":"https://github.com/kkakkkka/etris/blob/HEAD/model/layers.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89f9fd49ddec76ba"}},{"code_sha256_prefix":"78241a45492d6667","entry":"trainMetricGPU","repo":"kkakkkka/etris","repo_kind":"official","path":"utils/misc.py","file_url":"https://github.com/kkakkkka/etris/blob/HEAD/utils/misc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78241a45492d6667"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"kkakkkka/etris","repo_kind":"official","path":"utils/simple_tokenizer.py","file_url":"https://github.com/kkakkkka/etris/blob/HEAD/utils/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"23af313e4b569833","entry":"Bridger_RN","repo":"kkakkkka/ETRIS","repo_kind":"official","path":"model/bridger.py","file_url":"https://github.com/kkakkkka/ETRIS/blob/HEAD/model/bridger.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"23af313e4b569833"}},{"code_sha256_prefix":"98ab2f374bc768a9","entry":"adapt_position_encoding","repo":"kkakkkka/etris","repo_kind":"official","path":"model/clip.py","file_url":"https://github.com/kkakkkka/etris/blob/HEAD/model/clip.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98ab2f374bc768a9"}},{"code_sha256_prefix":"a77119da98b6e547","entry":"build_model","repo":"kkakkkka/etris","repo_kind":"official","path":"model/clip.py","file_url":"https://github.com/kkakkkka/etris/blob/HEAD/model/clip.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a77119da98b6e547"}},{"code_sha256_prefix":"73cecca9f3575f09","entry":"concat_all_gather","repo":"kkakkkka/etris","repo_kind":"official","path":"utils/misc.py","file_url":"https://github.com/kkakkkka/etris/blob/HEAD/utils/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73cecca9f3575f09"}},{"code_sha256_prefix":"db55fb2ff4ac93bb","entry":"deconv_layer","repo":"kkakkkka/etris","repo_kind":"official","path":"model/layers.py","file_url":"https://github.com/kkakkkka/etris/blob/HEAD/model/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"db55fb2ff4ac93bb"}},{"code_sha256_prefix":"cc23416cff396c39","entry":"load_cfg_from_cfg_file","repo":"kkakkkka/etris","repo_kind":"official","path":"utils/config.py","file_url":"https://github.com/kkakkkka/etris/blob/HEAD/utils/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cc23416cff396c39"}},{"code_sha256_prefix":"b4c154b6f0568b6b","entry":"loads_pyarrow","repo":"kkakkkka/etris","repo_kind":"official","path":"utils/dataset.py","file_url":"https://github.com/kkakkkka/etris/blob/HEAD/utils/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b4c154b6f0568b6b"}},{"code_sha256_prefix":"022883c7911679b3","entry":"merge_cfg_from_list","repo":"kkakkkka/etris","repo_kind":"official","path":"utils/config.py","file_url":"https://github.com/kkakkkka/etris/blob/HEAD/utils/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"022883c7911679b3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}