{"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/vision-language-models-are-strong-noisy-label","title":"Vision-Language Models are Strong Noisy Label Detectors","arxiv_id":"2409.19696","date":"2024-09-29","proceeding":null,"authors":["Tong Wei","Hao-Tian Li","Chun-Shu Li","Jiang-Xin Shi","Yu-Feng Li","Min-Ling Zhang"],"abstract":"Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a significant obstacle during the fine-tuning process. To address this challenge, this paper presents a Denoising Fine-Tuning framework, called DeFT, for adapting vision-language models. DeFT utilizes the robust alignment of textual and visual features pre-trained on millions of auxiliary image-text pairs to sieve out noisy labels. The proposed framework establishes a noisy label detector by learning positive and negative textual prompts for each class. The positive prompt seeks to reveal distinctive features of the class, while the negative prompt serves as a learnable threshold for separating clean and noisy samples. We employ parameter-efficient fine-tuning for the adaptation of a pre-trained visual encoder to promote its alignment with the learned textual prompts. As a general framework, DeFT can seamlessly fine-tune many pre-trained models to downstream tasks by utilizing carefully selected clean samples. Experimental results on seven synthetic and real-world noisy datasets validate the effectiveness of DeFT in both noisy label detection and image classification.","url_abs":"https://arxiv.org/abs/2409.19696v1","url_pdf":"https://arxiv.org/pdf/2409.19696v1.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":"vision-language-models-are-strong-noisy-label","repo_url":"https://github.com/HotanLee/DeFT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.19696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19696"}},"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/HotanLee/DeFT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":6},"by_repo_kind":{"official":{"samples":8,"ran":2,"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":"579bce41ae2654f3","entry":"CLIP_ViT","repo":"hotanlee/deft","repo_kind":"official","path":"model/CLIP.py","file_url":"https://github.com/hotanlee/deft/blob/HEAD/model/CLIP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"579bce41ae2654f3"}},{"code_sha256_prefix":"8da4e3661575688d","entry":"loss_coteaching","repo":"HotanLee/DeFT","repo_kind":"official","path":"main_small_loss.py","file_url":"https://github.com/HotanLee/DeFT/blob/HEAD/main_small_loss.py","link_basis":"first_harvest_node","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":"8da4e3661575688d"}},{"code_sha256_prefix":"3c0179f2c08e061b","entry":"Model","repo":"hotanlee/deft","repo_kind":"official","path":"model/CLIP.py","file_url":"https://github.com/hotanlee/deft/blob/HEAD/model/CLIP.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":"3c0179f2c08e061b"}},{"code_sha256_prefix":"7d006c94f1996e46","entry":"ViT_Tuner","repo":"hotanlee/deft","repo_kind":"official","path":"model/CLIP.py","file_url":"https://github.com/hotanlee/deft/blob/HEAD/model/CLIP.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":"7d006c94f1996e46"}},{"code_sha256_prefix":"15d083c0f312bf98","entry":"build_loader","repo":"HotanLee/DeFT","repo_kind":"official","path":"dataloader/dataloader_tiny_imagenet.py","file_url":"https://github.com/HotanLee/DeFT/blob/HEAD/dataloader/dataloader_tiny_imagenet.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":"15d083c0f312bf98"}},{"code_sha256_prefix":"514531c5f0f598b8","entry":"eval_train","repo":"HotanLee/DeFT","repo_kind":"official","path":"main_real_baseline.py","file_url":"https://github.com/HotanLee/DeFT/blob/HEAD/main_real_baseline.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":"514531c5f0f598b8"}},{"code_sha256_prefix":"db80cb31193f92b1","entry":"test","repo":"HotanLee/DeFT","repo_kind":"official","path":"main_small_loss.py","file_url":"https://github.com/HotanLee/DeFT/blob/HEAD/main_small_loss.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":"db80cb31193f92b1"}},{"code_sha256_prefix":"c8a8e3f0b597c1e7","entry":"test","repo":"HotanLee/DeFT","repo_kind":"official","path":"main_phase1.py","file_url":"https://github.com/HotanLee/DeFT/blob/HEAD/main_phase1.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":"c8a8e3f0b597c1e7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}