{"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/siri-a-simple-selective-retraining-mechanism","title":"SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding","arxiv_id":"2207.13325","date":"2022-07-27","proceeding":null,"authors":["Mengxue Qu","Yu Wu","Wu Liu","Qiqi Gong","Xiaodan Liang","Olga Russakovsky","Yao Zhao","Yunchao Wei"],"abstract":"In this paper, we investigate how to achieve better visual grounding with modern vision-language transformers, and propose a simple yet powerful Selective Retraining (SiRi) mechanism for this challenging task. Particularly, SiRi conveys a significant principle to the research of visual grounding, i.e., a better initialized vision-language encoder would help the model converge to a better local minimum, advancing the performance accordingly. In specific, we continually update the parameters of the encoder as the training goes on, while periodically re-initialize rest of the parameters to compel the model to be better optimized based on an enhanced encoder. SiRi can significantly outperform previous approaches on three popular benchmarks. Specifically, our method achieves 83.04% Top1 accuracy on RefCOCO+ testA, outperforming the state-of-the-art approaches (training from scratch) by more than 10.21%. Additionally, we reveal that SiRi performs surprisingly superior even with limited training data. We also extend it to transformer-based visual grounding models and other vision-language tasks to verify the validity.","url_abs":"https://arxiv.org/abs/2207.13325v1","url_pdf":"https://arxiv.org/pdf/2207.13325v1.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":"siri-a-simple-selective-retraining-mechanism","repo_url":"https://github.com/qumengxue/siri-vg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2207.13325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.13325"}},"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":"deterministic:regex_extraction","url":"https://github.com/qumengxue/siri-vg","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_violates":2,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"ac8fe530cdad4d8c","entry":"dice_loss","repo":"qumengxue/siri-vg","repo_kind":"official","path":"models/segmentation.py","file_url":"https://github.com/qumengxue/siri-vg/blob/HEAD/models/segmentation.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ac8fe530cdad4d8c"}},{"code_sha256_prefix":"86c7147edb17dd5d","entry":"normalization","repo":"qumengxue/siri-vg","repo_kind":"official","path":"models/gauss_map.py","file_url":"https://github.com/qumengxue/siri-vg/blob/HEAD/models/gauss_map.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86c7147edb17dd5d"}},{"code_sha256_prefix":"5c0711aada67957e","entry":"sigmoid_focal_loss","repo":"qumengxue/siri-vg","repo_kind":"official","path":"models/segmentation.py","file_url":"https://github.com/qumengxue/siri-vg/blob/HEAD/models/segmentation.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"code_sha256_prefix":"cea3f92defccfb9c","entry":"build_position_encoding","repo":"qumengxue/siri-vg","repo_kind":"official","path":"models/position_encoding.py","file_url":"https://github.com/qumengxue/siri-vg/blob/HEAD/models/position_encoding.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cea3f92defccfb9c"}},{"code_sha256_prefix":"f8cea2a98b3268dd","entry":"build_transformer","repo":"qumengxue/siri-vg","repo_kind":"official","path":"models/transformer.py","file_url":"https://github.com/qumengxue/siri-vg/blob/HEAD/models/transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f8cea2a98b3268dd"}},{"code_sha256_prefix":"7ab3fd5b2e774fce","entry":"create_positive_map","repo":"qumengxue/siri-vg","repo_kind":"official","path":"datasets/coco.py","file_url":"https://github.com/qumengxue/siri-vg/blob/HEAD/datasets/coco.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7ab3fd5b2e774fce"}},{"code_sha256_prefix":"c00698a63ab2ede9","entry":"get_proposal_pos_embed","repo":"qumengxue/siri-vg","repo_kind":"official","path":"models/gauss_map.py","file_url":"https://github.com/qumengxue/siri-vg/blob/HEAD/models/gauss_map.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c00698a63ab2ede9"}},{"code_sha256_prefix":"27b7ba6150ab74d3","entry":"make_gaussian","repo":"qumengxue/siri-vg","repo_kind":"official","path":"models/gauss_map.py","file_url":"https://github.com/qumengxue/siri-vg/blob/HEAD/models/gauss_map.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"27b7ba6150ab74d3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}