{"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/volta-vision-language-transformer-with-weakly","title":"VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment","arxiv_id":"2210.04135","date":"2022-10-09","proceeding":null,"authors":["Shraman Pramanick","Li Jing","Sayan Nag","Jiachen Zhu","Hardik Shah","Yann Lecun","Rama Chellappa"],"abstract":"Vision-language pre-training (VLP) has recently proven highly effective for various uni- and multi-modal downstream applications. However, most existing end-to-end VLP methods use high-resolution image-text box data to perform well on fine-grained region-level tasks, such as object detection, segmentation, and referring expression comprehension. Unfortunately, such high-resolution images with accurate bounding box annotations are expensive to collect and use for supervision at scale. In this work, we propose VoLTA (Vision-Language Transformer with weakly-supervised local-feature Alignment), a new VLP paradigm that only utilizes image-caption data but achieves fine-grained region-level image understanding, eliminating the use of expensive box annotations. VoLTA adopts graph optimal transport-based weakly-supervised alignment on local image patches and text tokens to germinate an explicit, self-normalized, and interpretable low-level matching criterion. In addition, VoLTA pushes multi-modal fusion deep into the uni-modal backbones during pre-training and removes fusion-specific transformer layers, further reducing memory requirements. Extensive experiments on a wide range of vision- and vision-language downstream tasks demonstrate the effectiveness of VoLTA on fine-grained applications without compromising the coarse-grained downstream performance, often outperforming methods using significantly more caption and box annotations.","url_abs":"https://arxiv.org/abs/2210.04135v3","url_pdf":"https://arxiv.org/pdf/2210.04135v3.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":"volta-vision-language-transformer-with-weakly","repo_url":"https://github.com/ShramanPramanick/VoLTA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.04135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.04135"}},"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/ShramanPramanick/VoLTA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_draft_wrong":2,"ran_honours":1,"ran_fixture":1,"unverified":8},"by_repo_kind":{"official":{"samples":12,"ran":4,"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":2,"samples":[{"code_sha256_prefix":"d79fd2ac61421292","entry":"cost_matrix_torch","repo":"ShramanPramanick/VoLTA","repo_kind":"official","path":"Pre-training/OT_torch_.py","file_url":"https://github.com/ShramanPramanick/VoLTA/blob/HEAD/Pre-training/OT_torch_.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d79fd2ac61421292"}},{"code_sha256_prefix":"da1c54dffed5d60c","entry":"create_position_ids_from_input_ids","repo":"ShramanPramanick/VoLTA","repo_kind":"official","path":"Pre-training/roberta.py","file_url":"https://github.com/ShramanPramanick/VoLTA/blob/HEAD/Pre-training/roberta.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da1c54dffed5d60c"}},{"code_sha256_prefix":"525b77c721203779","entry":"create_positive_map","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"525b77c721203779"}},{"code_sha256_prefix":"ea2c188d68558611","entry":"create_positive_map_label_to_token_from_positive_map","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ea2c188d68558611"}},{"code_sha256_prefix":"993ae96666b00cb5","entry":"window_partition","repo":"ShramanPramanick/VoLTA","repo_kind":"official","path":"Pre-training/swin_transformer.py","file_url":"https://github.com/ShramanPramanick/VoLTA/blob/HEAD/Pre-training/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"993ae96666b00cb5"}},{"code_sha256_prefix":"265c72d3ccc64544","entry":"window_reverse","repo":"ShramanPramanick/VoLTA","repo_kind":"official","path":"Pre-training/swin_transformer.py","file_url":"https://github.com/ShramanPramanick/VoLTA/blob/HEAD/Pre-training/swin_transformer.py","link_basis":"harvester_set","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":"265c72d3ccc64544"}},{"code_sha256_prefix":"b1e24c9598daad69","entry":"IPOT_distance_torch","repo":"ShramanPramanick/VoLTA","repo_kind":"official","path":"Pre-training/OT_torch_.py","file_url":"https://github.com/ShramanPramanick/VoLTA/blob/HEAD/Pre-training/OT_torch_.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":"b1e24c9598daad69"}},{"code_sha256_prefix":"674f9140f14e54a6","entry":"IPOT_torch","repo":"ShramanPramanick/VoLTA","repo_kind":"official","path":"Pre-training/OT_torch_.py","file_url":"https://github.com/ShramanPramanick/VoLTA/blob/HEAD/Pre-training/OT_torch_.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":"674f9140f14e54a6"}},{"code_sha256_prefix":"7a80cf522c830aeb","entry":"apply_chunking_to_forward","repo":"ShramanPramanick/VoLTA","repo_kind":"official","path":"Pre-training/roberta.py","file_url":"https://github.com/ShramanPramanick/VoLTA/blob/HEAD/Pre-training/roberta.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":"7a80cf522c830aeb"}},{"code_sha256_prefix":"c98d2b87e8adc438","entry":"get_id_list_coco2014","repo":"ShramanPramanick/VoLTA","repo_kind":"official","path":"Pre-training/get_id_list.py","file_url":"https://github.com/ShramanPramanick/VoLTA/blob/HEAD/Pre-training/get_id_list.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":"c98d2b87e8adc438"}},{"code_sha256_prefix":"33e998e445a0eee0","entry":"get_id_list_separate","repo":"ShramanPramanick/VoLTA","repo_kind":"official","path":"Pre-training/get_id_list.py","file_url":"https://github.com/ShramanPramanick/VoLTA/blob/HEAD/Pre-training/get_id_list.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":"33e998e445a0eee0"}},{"code_sha256_prefix":"bc3a13e8155e8140","entry":"load_state_dict","repo":"ShramanPramanick/VoLTA","repo_kind":"official","path":"Pre-training/swin_helpers.py","file_url":"https://github.com/ShramanPramanick/VoLTA/blob/HEAD/Pre-training/swin_helpers.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":"bc3a13e8155e8140"}},{"code_sha256_prefix":"102b75f3481035d1","entry":"resume_checkpoint","repo":"ShramanPramanick/VoLTA","repo_kind":"official","path":"Pre-training/swin_helpers.py","file_url":"https://github.com/ShramanPramanick/VoLTA/blob/HEAD/Pre-training/swin_helpers.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":"102b75f3481035d1"}},{"code_sha256_prefix":"3c0bf9aa4752cff5","entry":"swin_adapt_position_encoding","repo":"ShramanPramanick/VoLTA","repo_kind":"official","path":"Pre-training/swin_helpers.py","file_url":"https://github.com/ShramanPramanick/VoLTA/blob/HEAD/Pre-training/swin_helpers.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":"3c0bf9aa4752cff5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}