{"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/long-term-cross-adversarial-training-a-robust","title":"Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Tasks","arxiv_id":"2106.12900","date":"2021-06-22","proceeding":"ICML Workshop AML 2021 7","authors":["Fan Liu","Shuyu Zhao","Xuelong Dai","Bin Xiao"],"abstract":"Meta-learning model can quickly adapt to new tasks using few-shot labeled data. However, despite achieving good generalization on few-shot classification tasks, it is still challenging to improve the adversarial robustness of the meta-learning model in few-shot learning. Although adversarial training (AT) methods such as Adversarial Query (AQ) can improve the adversarially robust performance of meta-learning models, AT is still computationally expensive training. On the other hand, meta-learning models trained with AT will drop significant accuracy on the original clean images. This paper proposed a meta-learning method on the adversarially robust neural network called Long-term Cross Adversarial Training (LCAT). LCAT will update meta-learning model parameters cross along the natural and adversarial sample distribution direction with long-term to improve both adversarial and clean few-shot classification accuracy. Due to cross-adversarial training, LCAT only needs half of the adversarial training epoch than AQ, resulting in a low adversarial training computation. Experiment results show that LCAT achieves superior performance both on the clean and adversarial few-shot classification accuracy than SOTA adversarial training methods for meta-learning models.","url_abs":"https://arxiv.org/abs/2106.12900v3","url_pdf":"https://arxiv.org/pdf/2106.12900v3.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":"long-term-cross-adversarial-training-a-robust","repo_url":"https://github.com/Gnomeek/Long-term-Cross-Adversarial-Training","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.12900","atlas_url":"https://app.syntology.ai/?focus=2106.12900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12900"}},"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/Gnomeek/Long-term-Cross-Adversarial-Training","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":8},"by_repo_kind":{"official":{"samples":9,"ran":1,"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":"dfb410b516603bd0","entry":"batched_kronecker","repo":"Gnomeek/Long-term-Cross-Adversarial-Training","repo_kind":"official","path":"models/classification_heads.py","file_url":"https://github.com/Gnomeek/Long-term-Cross-Adversarial-Training/blob/HEAD/models/classification_heads.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dfb410b516603bd0"}},{"code_sha256_prefix":"f91e7aca05358b42","entry":"ClassificationHead","repo":"Gnomeek/Long-term-Cross-Adversarial-Training","repo_kind":"official","path":"models/classification_heads.py","file_url":"https://github.com/Gnomeek/Long-term-Cross-Adversarial-Training/blob/HEAD/models/classification_heads.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":"f91e7aca05358b42"}},{"code_sha256_prefix":"164d6cbdfbe35a4c","entry":"MetaOptNetHead_Ridge","repo":"Gnomeek/Long-term-Cross-Adversarial-Training","repo_kind":"official","path":"models/classification_heads.py","file_url":"https://github.com/Gnomeek/Long-term-Cross-Adversarial-Training/blob/HEAD/models/classification_heads.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":"164d6cbdfbe35a4c"}},{"code_sha256_prefix":"d24c33e70255520f","entry":"MetaOptNetHead_SVM_CS","repo":"Gnomeek/Long-term-Cross-Adversarial-Training","repo_kind":"official","path":"models/classification_heads.py","file_url":"https://github.com/Gnomeek/Long-term-Cross-Adversarial-Training/blob/HEAD/models/classification_heads.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":"d24c33e70255520f"}},{"code_sha256_prefix":"7025f6cd07c8888d","entry":"MetaOptNetHead_SVM_He","repo":"Gnomeek/Long-term-Cross-Adversarial-Training","repo_kind":"official","path":"models/classification_heads.py","file_url":"https://github.com/Gnomeek/Long-term-Cross-Adversarial-Training/blob/HEAD/models/classification_heads.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":"7025f6cd07c8888d"}},{"code_sha256_prefix":"1fc61108dee7366d","entry":"MetaOptNetHead_SVM_WW","repo":"Gnomeek/Long-term-Cross-Adversarial-Training","repo_kind":"official","path":"models/classification_heads.py","file_url":"https://github.com/Gnomeek/Long-term-Cross-Adversarial-Training/blob/HEAD/models/classification_heads.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":"1fc61108dee7366d"}},{"code_sha256_prefix":"cbfcebbb92aa2d91","entry":"QPFunction","repo":"Gnomeek/Long-term-Cross-Adversarial-Training","repo_kind":"official","path":"models/classification_heads.py","file_url":"https://github.com/Gnomeek/Long-term-Cross-Adversarial-Training/blob/HEAD/models/classification_heads.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":"cbfcebbb92aa2d91"}},{"code_sha256_prefix":"4ba66190e169c728","entry":"R2D2Head","repo":"Gnomeek/Long-term-Cross-Adversarial-Training","repo_kind":"official","path":"models/classification_heads.py","file_url":"https://github.com/Gnomeek/Long-term-Cross-Adversarial-Training/blob/HEAD/models/classification_heads.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":"4ba66190e169c728"}},{"code_sha256_prefix":"aaa83879ae347071","entry":"binv","repo":"Gnomeek/Long-term-Cross-Adversarial-Training","repo_kind":"official","path":"models/classification_heads.py","file_url":"https://github.com/Gnomeek/Long-term-Cross-Adversarial-Training/blob/HEAD/models/classification_heads.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":"aaa83879ae347071"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}