{"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/similarity-reasoning-and-filtration-for-image","title":"Similarity Reasoning and Filtration for Image-Text Matching","arxiv_id":"2101.01368","date":"2021-01-05","proceeding":null,"authors":["Haiwen Diao","Ying Zhang","Lin Ma","Huchuan Lu"],"abstract":"Image-text matching plays a critical role in bridging the vision and language, and great progress has been made by exploiting the global alignment between image and sentence, or local alignments between regions and words. However, how to make the most of these alignments to infer more accurate matching scores is still underexplored. In this paper, we propose a novel Similarity Graph Reasoning and Attention Filtration (SGRAF) network for image-text matching. Specifically, the vector-based similarity representations are firstly learned to characterize the local and global alignments in a more comprehensive manner, and then the Similarity Graph Reasoning (SGR) module relying on one graph convolutional neural network is introduced to infer relation-aware similarities with both the local and global alignments. The Similarity Attention Filtration (SAF) module is further developed to integrate these alignments effectively by selectively attending on the significant and representative alignments and meanwhile casting aside the interferences of non-meaningful alignments. We demonstrate the superiority of the proposed method with achieving state-of-the-art performances on the Flickr30K and MSCOCO datasets, and the good interpretability of SGR and SAF modules with extensive qualitative experiments and analyses.","url_abs":"https://arxiv.org/abs/2101.01368v1","url_pdf":"https://arxiv.org/pdf/2101.01368v1.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":"similarity-reasoning-and-filtration-for-image","repo_url":"https://github.com/Paranioar/SGRAF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"image-text-matching","task_name":"Image-text matching"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-retrieval","task_name":"Sentence Retrieval"},{"task_slug":"text-matching","task_name":"Text Matching"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-modal-retrieval-on-coco-2014","task":"Cross-Modal Retrieval","dataset":"COCO 2014","model":"SGRAF","rank_in_archive_order":28,"of":36,"metrics":{"Image-to-text R@1":"57.8","Image-to-text R@10":"91.6","Image-to-text R@5":"84.9","Text-to-image R@1":"41.9","Text-to-image R@10":"81.3","Text-to-image R@5":"70.7"},"uses_additional_data":false},{"leaderboard":"/sota/cross-modal-retrieval-on-flickr30k","task":"Cross-Modal Retrieval","dataset":"Flickr30k","model":"SGRAF","rank_in_archive_order":17,"of":27,"metrics":{"Image-to-text R@1":"77.8","Image-to-text R@10":"97.4","Image-to-text R@5":"94.1","Text-to-image R@1":"58.5","Text-to-image R@10":"88.8","Text-to-image R@5":"83.0"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-flickr30k-1k-test","task":"Image Retrieval","dataset":"Flickr30K 1K test","model":"SGRAF","rank_in_archive_order":3,"of":18,"metrics":{"R@1":"58.5","R@10":"88.8","R@5":"83.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.01368","atlas_url":"https://app.syntology.ai/?focus=2101.01368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.01368"}},"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":"deterministic:regex_extraction","url":"https://github.com/Paranioar/SGRAF","reach":null}],"summary":{"ran":7,"ran_fixture":1,"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":12,"ran":10,"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":12,"samples":[{"code_sha256_prefix":"c6025b866d2b9405","entry":"AttentionFiltration","repo":"Paranioar/SGRAF","repo_kind":"official","path":"model.py","file_url":"https://github.com/Paranioar/SGRAF/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c6025b866d2b9405"}},{"code_sha256_prefix":"94a076af96564b32","entry":"ContrastiveLoss","repo":"Paranioar/SGRAF","repo_kind":"official","path":"model.py","file_url":"https://github.com/Paranioar/SGRAF/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"94a076af96564b32"}},{"code_sha256_prefix":"c4d232eaafd32247","entry":"EncoderImage","repo":"Paranioar/SGRAF","repo_kind":"official","path":"model.py","file_url":"https://github.com/Paranioar/SGRAF/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c4d232eaafd32247"}},{"code_sha256_prefix":"8e98d766a117968f","entry":"EncoderText","repo":"Paranioar/SGRAF","repo_kind":"official","path":"model.py","file_url":"https://github.com/Paranioar/SGRAF/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8e98d766a117968f"}},{"code_sha256_prefix":"42172bf6d3276ede","entry":"GraphReasoning","repo":"Paranioar/SGRAF","repo_kind":"official","path":"model.py","file_url":"https://github.com/Paranioar/SGRAF/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"42172bf6d3276ede"}},{"code_sha256_prefix":"7ec3bfb5f7f9023e","entry":"SCAN_attention","repo":"Paranioar/SGRAF","repo_kind":"official","path":"model.py","file_url":"https://github.com/Paranioar/SGRAF/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7ec3bfb5f7f9023e"}},{"code_sha256_prefix":"c5dcf5e3dad7dc3c","entry":"TextSA","repo":"Paranioar/SGRAF","repo_kind":"official","path":"model.py","file_url":"https://github.com/Paranioar/SGRAF/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c5dcf5e3dad7dc3c"}},{"code_sha256_prefix":"9ebccf24c4d94b35","entry":"VisualSA","repo":"Paranioar/SGRAF","repo_kind":"official","path":"model.py","file_url":"https://github.com/Paranioar/SGRAF/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9ebccf24c4d94b35"}},{"code_sha256_prefix":"b943467457f9825d","entry":"l1norm","repo":"Paranioar/SGRAF","repo_kind":"official","path":"model.py","file_url":"https://github.com/Paranioar/SGRAF/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b943467457f9825d"}},{"code_sha256_prefix":"03e1f23d59a7c45a","entry":"l2norm","repo":"Paranioar/SGRAF","repo_kind":"official","path":"model.py","file_url":"https://github.com/Paranioar/SGRAF/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"03e1f23d59a7c45a"}},{"code_sha256_prefix":"aecc8b84c92f1722","entry":"EncoderSimilarity","repo":"Paranioar/SGRAF","repo_kind":"official","path":"model.py","file_url":"https://github.com/Paranioar/SGRAF/blob/HEAD/model.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":"aecc8b84c92f1722"}},{"code_sha256_prefix":"5b760d12978789a0","entry":"SGRAF","repo":"Paranioar/SGRAF","repo_kind":"official","path":"model.py","file_url":"https://github.com/Paranioar/SGRAF/blob/HEAD/model.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":"5b760d12978789a0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}