{"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/webly-supervised-image-classification-with","title":"Webly Supervised Image Classification with Self-Contained Confidence","arxiv_id":"2008.11894","date":"2020-08-27","proceeding":"ECCV 2020 8","authors":["Jingkang Yang","Litong Feng","Weirong Chen","Xiaopeng Yan","Huabin Zheng","Ping Luo","Wayne Zhang"],"abstract":"This paper focuses on webly supervised learning (WSL), where datasets are built by crawling samples from the Internet and directly using search queries as web labels. Although WSL benefits from fast and low-cost data collection, noises in web labels hinder better performance of the image classification model. To alleviate this problem, in recent works, self-label supervised loss $\\mathcal{L}_s$ is utilized together with webly supervised loss $\\mathcal{L}_w$. $\\mathcal{L}_s$ relies on pseudo labels predicted by the model itself. Since the correctness of the web label or pseudo label is usually on a case-by-case basis for each web sample, it is desirable to adjust the balance between $\\mathcal{L}_s$ and $\\mathcal{L}_w$ on sample level. Inspired by the ability of Deep Neural Networks (DNNs) in confidence prediction, we introduce Self-Contained Confidence (SCC) by adapting model uncertainty for WSL setting, and use it to sample-wisely balance $\\mathcal{L}_s$ and $\\mathcal{L}_w$. Therefore, a simple yet effective WSL framework is proposed. A series of SCC-friendly regularization approaches are investigated, among which the proposed graph-enhanced mixup is the most effective method to provide high-quality confidence to enhance our framework. The proposed WSL framework has achieved the state-of-the-art results on two large-scale WSL datasets, WebVision-1000 and Food101-N. Code is available at https://github.com/bigvideoresearch/SCC.","url_abs":"https://arxiv.org/abs/2008.11894v1","url_pdf":"https://arxiv.org/pdf/2008.11894v1.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":"webly-supervised-image-classification-with","repo_url":"https://github.com/bigvideoresearch/SCC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"webly-supervised-image-classification-with","repo_url":"https://github.com/bigvideoresearch/Enigma","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"webly-supervised-image-classification-with","repo_url":"https://github.com/yuleiqin/capro","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"webly-supervised-image-classification-with","repo_url":"https://github.com/yuleiqin/fopro","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-webvision-1000","task":"Image Classification","dataset":"WebVision-1000","model":"SCC (ResNet50-D)","rank_in_archive_order":7,"of":16,"metrics":{"ImageNet Top-1 Accuracy":"70.66%","ImageNet Top-5 Accuracy":"88.46%","Top-1 Accuracy":"75.78%","Top-5 Accuracy":"91.07%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2008.11894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.11894"}},"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/yuleiqin/fopro","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bigvideoresearch/SCC","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bigvideoresearch/Enigma","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yuleiqin/capro","reach":{"status":"ok"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":2}},"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":"133e21885ae6f12c","entry":"ScalingConf","repo":"bigvideoresearch/SCC","repo_kind":"official","path":"pipelines/WSL/offline_SCC_patch.py","file_url":"https://github.com/bigvideoresearch/SCC/blob/HEAD/pipelines/WSL/offline_SCC_patch.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":"133e21885ae6f12c"}},{"code_sha256_prefix":"ca69a3b5333e24c4","entry":"get_reweight_ratio","repo":"bigvideoresearch/Enigma","repo_kind":"official","path":"labelers/offline_cnn/distribute_score_file.py","file_url":"https://github.com/bigvideoresearch/Enigma/blob/HEAD/labelers/offline_cnn/distribute_score_file.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":"ca69a3b5333e24c4"}},{"code_sha256_prefix":"4ec67b531c5163a6","entry":"getlabelarray","repo":"bigvideoresearch/Enigma","repo_kind":"official","path":"labelers/offline_cnn/distribute_score_file.py","file_url":"https://github.com/bigvideoresearch/Enigma/blob/HEAD/labelers/offline_cnn/distribute_score_file.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":"4ec67b531c5163a6"}},{"code_sha256_prefix":"3e094dea6933cefe","entry":"modify","repo":"bigvideoresearch/Enigma","repo_kind":"official","path":"networks/resnet_modify.py","file_url":"https://github.com/bigvideoresearch/Enigma/blob/HEAD/networks/resnet_modify.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":"3e094dea6933cefe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}