{"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/learn-from-all-erasing-attention-consistency","title":"Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition","arxiv_id":"2207.10299","date":"2022-07-21","proceeding":null,"authors":["Yuhang Zhang","Chengrui Wang","Xu Ling","Weihong Deng"],"abstract":"Noisy label Facial Expression Recognition (FER) is more challenging than traditional noisy label classification tasks due to the inter-class similarity and the annotation ambiguity. Recent works mainly tackle this problem by filtering out large-loss samples. In this paper, we explore dealing with noisy labels from a new feature-learning perspective. We find that FER models remember noisy samples by focusing on a part of the features that can be considered related to the noisy labels instead of learning from the whole features that lead to the latent truth. Inspired by that, we propose a novel Erasing Attention Consistency (EAC) method to suppress the noisy samples during the training process automatically. Specifically, we first utilize the flip semantic consistency of facial images to design an imbalanced framework. We then randomly erase input images and use flip attention consistency to prevent the model from focusing on a part of the features. EAC significantly outperforms state-of-the-art noisy label FER methods and generalizes well to other tasks with a large number of classes like CIFAR100 and Tiny-ImageNet. The code is available at https://github.com/zyh-uaiaaaa/Erasing-Attention-Consistency.","url_abs":"https://arxiv.org/abs/2207.10299v2","url_pdf":"https://arxiv.org/pdf/2207.10299v2.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":"learn-from-all-erasing-attention-consistency","repo_url":"https://github.com/zyh-uaiaaaa/erasing-attention-consistency","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"facial-expression-recognition-1","task_name":"Facial Expression Recognition"},{"task_slug":"facial-expression-recognition","task_name":"Facial Expression Recognition (FER)"},{"task_slug":"learning-with-noisy-labels","task_name":"Learning with noisy labels"}],"methods":[{"method_slug":"flip","method_name":"FLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/facial-expression-recognition-on-acted-facial","task":"Facial Expression Recognition (FER)","dataset":"Acted Facial Expressions In The Wild (AFEW)","model":"EAC","rank_in_archive_order":3,"of":8,"metrics":{"Accuracy(on validation set)":"65.32%"},"uses_additional_data":false},{"leaderboard":"/sota/facial-expression-recognition-on-affectnet","task":"Facial Expression Recognition (FER)","dataset":"AffectNet","model":"EAC","rank_in_archive_order":43,"of":50,"metrics":{"Accuracy (7 emotion)":"65.32"},"uses_additional_data":false},{"leaderboard":"/sota/facial-expression-recognition-on-fer-1","task":"Facial Expression Recognition (FER)","dataset":"FER+","model":"EAC","rank_in_archive_order":9,"of":14,"metrics":{"Accuracy":"89.64"},"uses_additional_data":false},{"leaderboard":"/sota/facial-expression-recognition-on-raf-db","task":"Facial Expression Recognition (FER)","dataset":"RAF-DB","model":"EAC(ResNet-50)","rank_in_archive_order":16,"of":35,"metrics":{"Overall Accuracy":"90.35"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.10299","atlas_url":"https://app.syntology.ai/?focus=2207.10299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10299"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/zyh-uaiaaaa/Erasing-Attention-Consistency","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"1e876a840c1a68de","entry":"ACLoss","repo":"zyh-uaiaaaa/Erasing-Attention-Consistency","repo_kind":"official","path":"src/loss.py","file_url":"https://github.com/zyh-uaiaaaa/Erasing-Attention-Consistency/blob/HEAD/src/loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1e876a840c1a68de"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}