{"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/conzic-controllable-zero-shot-image","title":"ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing","arxiv_id":"2303.02437","date":"2023-03-04","proceeding":"CVPR 2023 1","authors":["Zequn Zeng","Hao Zhang","Zhengjue Wang","Ruiying Lu","Dongsheng Wang","Bo Chen"],"abstract":"Zero-shot capability has been considered as a new revolution of deep learning, letting machines work on tasks without curated training data. As a good start and the only existing outcome of zero-shot image captioning (IC), ZeroCap abandons supervised training and sequentially searches every word in the caption using the knowledge of large-scale pretrained models. Though effective, its autoregressive generation and gradient-directed searching mechanism limit the diversity of captions and inference speed, respectively. Moreover, ZeroCap does not consider the controllability issue of zero-shot IC. To move forward, we propose a framework for Controllable Zero-shot IC, named ConZIC. The core of ConZIC is a novel sampling-based non-autoregressive language model named GibbsBERT, which can generate and continuously polish every word. Extensive quantitative and qualitative results demonstrate the superior performance of our proposed ConZIC for both zero-shot IC and controllable zero-shot IC. Especially, ConZIC achieves about 5x faster generation speed than ZeroCap, and about 1.5x higher diversity scores, with accurate generation given different control signals.","url_abs":"https://arxiv.org/abs/2303.02437v2","url_pdf":"https://arxiv.org/pdf/2303.02437v2.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":"conzic-controllable-zero-shot-image","repo_url":"https://github.com/joeyz0z/conzic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.02437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.02437"}},"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/joeyz0z/conzic","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/joeyz0z/ConZIC","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"ran_fixture":1,"unverified":7},"by_repo_kind":{"official":{"samples":10,"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":"7a2fccd6d2912eba","entry":"generate_caption_step","repo":"joeyz0z/ConZIC","repo_kind":"official","path":"control_gen_utils.py","file_url":"https://github.com/joeyz0z/ConZIC/blob/HEAD/control_gen_utils.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a2fccd6d2912eba"}},{"code_sha256_prefix":"580f8666594fcbf4","entry":"get_init_text","repo":"joeyz0z/ConZIC","repo_kind":"official","path":"control_gen_utils.py","file_url":"https://github.com/joeyz0z/ConZIC/blob/HEAD/control_gen_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"580f8666594fcbf4"}},{"code_sha256_prefix":"4a41705616e3bbca","entry":"update_token_mask","repo":"joeyz0z/ConZIC","repo_kind":"official","path":"control_gen_utils.py","file_url":"https://github.com/joeyz0z/ConZIC/blob/HEAD/control_gen_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4a41705616e3bbca"}},{"code_sha256_prefix":"932b4e2e1d9ac06e","entry":"POS_sequential_generation","repo":"joeyz0z/ConZIC","repo_kind":"official","path":"control_gen_utils.py","file_url":"https://github.com/joeyz0z/ConZIC/blob/HEAD/control_gen_utils.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":"932b4e2e1d9ac06e"}},{"code_sha256_prefix":"9e4e742ec3ee5af1","entry":"batch_texts_POS_Sentiments_analysis","repo":"joeyz0z/ConZIC","repo_kind":"official","path":"control_gen_utils.py","file_url":"https://github.com/joeyz0z/ConZIC/blob/HEAD/control_gen_utils.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":"9e4e742ec3ee5af1"}},{"code_sha256_prefix":"ea029a9ae14463cd","entry":"batch_texts_POS_analysis","repo":"joeyz0z/ConZIC","repo_kind":"official","path":"control_gen_utils.py","file_url":"https://github.com/joeyz0z/ConZIC/blob/HEAD/control_gen_utils.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":"ea029a9ae14463cd"}},{"code_sha256_prefix":"87c4eb6e2eb39819","entry":"control_generate_caption","repo":"joeyz0z/ConZIC","repo_kind":"official","path":"control_gen_utils.py","file_url":"https://github.com/joeyz0z/ConZIC/blob/HEAD/control_gen_utils.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":"87c4eb6e2eb39819"}},{"code_sha256_prefix":"545b48c4df087bad","entry":"sentiment_sequential_generation","repo":"joeyz0z/ConZIC","repo_kind":"official","path":"control_gen_utils.py","file_url":"https://github.com/joeyz0z/ConZIC/blob/HEAD/control_gen_utils.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":"545b48c4df087bad"}},{"code_sha256_prefix":"974e0fd37be015e7","entry":"sentiment_shuffle_generation","repo":"joeyz0z/ConZIC","repo_kind":"official","path":"control_gen_utils.py","file_url":"https://github.com/joeyz0z/ConZIC/blob/HEAD/control_gen_utils.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":"974e0fd37be015e7"}},{"code_sha256_prefix":"51cd62b886b4d5c2","entry":"text_POS_Sentiments_analysis","repo":"joeyz0z/ConZIC","repo_kind":"official","path":"control_gen_utils.py","file_url":"https://github.com/joeyz0z/ConZIC/blob/HEAD/control_gen_utils.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":"51cd62b886b4d5c2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}