{"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/noise-aware-learning-from-web-crawled-image","title":"Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning","arxiv_id":"2212.13563","date":"2022-12-27","proceeding":"ICCV 2023 1","authors":["Wooyoung Kang","Jonghwan Mun","Sungjun Lee","Byungseok Roh"],"abstract":"Image captioning is one of the straightforward tasks that can take advantage of large-scale web-crawled data which provides rich knowledge about the visual world for a captioning model. However, since web-crawled data contains image-text pairs that are aligned at different levels, the inherent noises (e.g., misaligned pairs) make it difficult to learn a precise captioning model. While the filtering strategy can effectively remove noisy data, it leads to a decrease in learnable knowledge and sometimes brings about a new problem of data deficiency. To take the best of both worlds, we propose a Noise-aware Captioning (NoC) framework, which learns rich knowledge from the whole web-crawled data while being less affected by the noises. This is achieved by the proposed alignment-level-controllable captioner, which is learned using alignment levels of the image-text pairs as a control signal during training. The alignment-level-conditioned training allows the model to generate high-quality captions by simply setting the control signal to the desired alignment level at inference time. An in-depth analysis shows the effectiveness of our framework in handling noise. With two tasks of zero-shot captioning and text-to-image retrieval using generated captions (i.e., self-retrieval), we also demonstrate our model can produce high-quality captions in terms of descriptiveness and distinctiveness. The code is available at \\url{https://github.com/kakaobrain/noc}.","url_abs":"https://arxiv.org/abs/2212.13563v2","url_pdf":"https://arxiv.org/pdf/2212.13563v2.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":"noise-aware-learning-from-web-crawled-image","repo_url":"https://github.com/kakaobrain/noc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.13563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13563"}},"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/kakaobrain/noc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"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":"98f385d847636a3e","entry":"basic_clean","repo":"kakaobrain/noc","repo_kind":"official","path":"noc/models/clip/simple_tokenizer.py","file_url":"https://github.com/kakaobrain/noc/blob/HEAD/noc/models/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"kakaobrain/noc","repo_kind":"official","path":"noc/models/clip/simple_tokenizer.py","file_url":"https://github.com/kakaobrain/noc/blob/HEAD/noc/models/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"kakaobrain/noc","repo_kind":"official","path":"noc/models/clip/simple_tokenizer.py","file_url":"https://github.com/kakaobrain/noc/blob/HEAD/noc/models/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"ddd4a2125358b46b","entry":"build_model","repo":"kakaobrain/noc","repo_kind":"official","path":"noc/models/clip/model.py","file_url":"https://github.com/kakaobrain/noc/blob/HEAD/noc/models/clip/model.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":"ddd4a2125358b46b"}},{"code_sha256_prefix":"907a99c74d56b0bd","entry":"build_transform","repo":"kakaobrain/noc","repo_kind":"official","path":"noc/dataset/transforms.py","file_url":"https://github.com/kakaobrain/noc/blob/HEAD/noc/dataset/transforms.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":"907a99c74d56b0bd"}},{"code_sha256_prefix":"a4aabd122dca5e8a","entry":"load","repo":"kakaobrain/noc","repo_kind":"official","path":"noc/models/clip/clip.py","file_url":"https://github.com/kakaobrain/noc/blob/HEAD/noc/models/clip/clip.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":"a4aabd122dca5e8a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}