{"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/segvg-transferring-object-bounding-box-to","title":"SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding","arxiv_id":"2407.03200","date":"2024-07-03","proceeding":null,"authors":["Weitai Kang","Gaowen Liu","Mubarak Shah","Yan Yan"],"abstract":"Different from Object Detection, Visual Grounding deals with detecting a bounding box for each text-image pair. This one box for each text-image data provides sparse supervision signals. Although previous works achieve impressive results, their passive utilization of annotation, i.e. the sole use of the box annotation as regression ground truth, results in a suboptimal performance. In this paper, we present SegVG, a novel method transfers the box-level annotation as Segmentation signals to provide an additional pixel-level supervision for Visual Grounding. Specifically, we propose the Multi-layer Multi-task Encoder-Decoder as the target grounding stage, where we learn a regression query and multiple segmentation queries to ground the target by regression and segmentation of the box in each decoding layer, respectively. This approach allows us to iteratively exploit the annotation as signals for both box-level regression and pixel-level segmentation. Moreover, as the backbones are typically initialized by pretrained parameters learned from unimodal tasks and the queries for both regression and segmentation are static learnable embeddings, a domain discrepancy remains among these three types of features, which impairs subsequent target grounding. To mitigate this discrepancy, we introduce the Triple Alignment module, where the query, text, and vision tokens are triangularly updated to share the same space by triple attention mechanism. Extensive experiments on five widely used datasets validate our state-of-the-art (SOTA) performance.","url_abs":"https://arxiv.org/abs/2407.03200v2","url_pdf":"https://arxiv.org/pdf/2407.03200v2.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":"segvg-transferring-object-bounding-box-to","repo_url":"https://github.com/weitaikang/segvg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"},{"task_slug":"object-detection-1","task_name":"object-detection"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2407.03200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03200"}},"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/WeitaiKang/SegVG","reach":null}],"summary":{"ran":15,"ran_draft_wrong":5,"unverified":11},"by_repo_kind":{"official":{"samples":31,"ran":20,"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":31,"samples":[{"code_sha256_prefix":"3cea0289236abff1","entry":"Backbone","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"3cea0289236abff1"}},{"code_sha256_prefix":"64ed5e61066db71b","entry":"BackboneBase","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"64ed5e61066db71b"}},{"code_sha256_prefix":"86783d5616cc10ae","entry":"DETR","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"86783d5616cc10ae"}},{"code_sha256_prefix":"edab1f7b54761edc","entry":"FrozenBatchNorm2d","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"edab1f7b54761edc"}},{"code_sha256_prefix":"83277abc6189fc0e","entry":"Joiner","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"83277abc6189fc0e"}},{"code_sha256_prefix":"1630454d42cd8f1e","entry":"MLP","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"1630454d42cd8f1e"}},{"code_sha256_prefix":"d232f407f48ea631","entry":"MultiheadAttention","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"d232f407f48ea631"}},{"code_sha256_prefix":"b636bcda4557023e","entry":"NestedTensor","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"b636bcda4557023e"}},{"code_sha256_prefix":"b088aa9b061f576f","entry":"PositionEmbeddingLearned","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"b088aa9b061f576f"}},{"code_sha256_prefix":"f6738d0ca7aecfc9","entry":"PositionEmbeddingSine","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"f6738d0ca7aecfc9"}},{"code_sha256_prefix":"3f84d490190e415e","entry":"TransformerDecoder","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"3f84d490190e415e"}},{"code_sha256_prefix":"cb39d54bf9488205","entry":"TransformerDecoderLayer","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"cb39d54bf9488205"}},{"code_sha256_prefix":"143c12efbf5e86a7","entry":"TransformerEncoder","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"143c12efbf5e86a7"}},{"code_sha256_prefix":"11325595a1e21029","entry":"TransformerEncoderLayer","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"11325595a1e21029"}},{"code_sha256_prefix":"8fadf62d0de39848","entry":"Triple_Alignment","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"8fadf62d0de39848"}},{"code_sha256_prefix":"0bb264f52e707e08","entry":"_get_activation_fn","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0bb264f52e707e08"}},{"code_sha256_prefix":"a8f1bbeb369e1829","entry":"_get_clones","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.py","link_basis":"first_harvest_node","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":"a8f1bbeb369e1829"}},{"code_sha256_prefix":"f07174e325e1d5a1","entry":"build_backbone","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.py","link_basis":"first_harvest_node","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":"f07174e325e1d5a1"}},{"code_sha256_prefix":"153726d9d215fcbd","entry":"build_position_encoding","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.py","link_basis":"first_harvest_node","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":"153726d9d215fcbd"}},{"code_sha256_prefix":"a7b239b27e836fef","entry":"nested_tensor_from_tensor_list","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.py","link_basis":"first_harvest_node","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":"a7b239b27e836fef"}},{"code_sha256_prefix":"98a92778fc361b78","entry":"CustomBertModelLayers","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"98a92778fc361b78"}},{"code_sha256_prefix":"a46b55dedcf54d6a","entry":"SegVG","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"a46b55dedcf54d6a"}},{"code_sha256_prefix":"7e21dc328864a039","entry":"Transformer","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"7e21dc328864a039"}},{"code_sha256_prefix":"b2c1a11b8bad9f0f","entry":"Triple_Alignment_MHA","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"b2c1a11b8bad9f0f"}},{"code_sha256_prefix":"be0f0a78676af033","entry":"VisionLanguageDecoder","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"be0f0a78676af033"}},{"code_sha256_prefix":"a9723207bca49592","entry":"VisionLanguageEncoder","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"a9723207bca49592"}},{"code_sha256_prefix":"18ab6b8c9071badc","entry":"_onnx_nested_tensor_from_tensor_list","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"18ab6b8c9071badc"}},{"code_sha256_prefix":"d094d16051634f8d","entry":"build_bert","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"d094d16051634f8d"}},{"code_sha256_prefix":"6dde8f71aadd6481","entry":"build_detr","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"6dde8f71aadd6481"}},{"code_sha256_prefix":"9008729eeca3ae5e","entry":"build_transformer","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"9008729eeca3ae5e"}},{"code_sha256_prefix":"fa56b4b60f836e92","entry":"build_vl_transformer","repo":"WeitaiKang/SegVG","repo_kind":"official","path":"models/SegVG.py","file_url":"https://github.com/WeitaiKang/SegVG/blob/HEAD/models/SegVG.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":"fa56b4b60f836e92"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}