{"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/fine-grained-visual-categorization-using-meta","title":"Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data","arxiv_id":"1807.10916","date":"2018-07-28","proceeding":"ECCV 2018 9","authors":["Yabin Zhang","Hui Tang","Kui Jia"],"abstract":"Fine-grained visual categorization (FGVC) is challenging due in part to the\nfact that it is often difficult to acquire an enough number of training\nsamples. To employ large models for FGVC without suffering from overfitting,\nexisting methods usually adopt a strategy of pre-training the models using a\nrich set of auxiliary data, followed by fine-tuning on the target FGVC task.\nHowever, the objective of pre-training does not take the target task into\naccount, and consequently such obtained models are suboptimal for fine-tuning.\nTo address this issue, we propose in this paper a new deep FGVC model termed\nMetaFGNet. Training of MetaFGNet is based on a novel regularized meta-learning\nobjective, which aims to guide the learning of network parameters so that they\nare optimal for adapting to the target FGVC task. Based on MetaFGNet, we also\npropose a simple yet effective scheme for selecting more useful samples from\nthe auxiliary data. Experiments on benchmark FGVC datasets show the efficacy of\nour proposed method.","url_abs":"http://arxiv.org/abs/1807.10916v1","url_pdf":"http://arxiv.org/pdf/1807.10916v1.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":"fine-grained-visual-categorization-using-meta","repo_url":"https://github.com/YBZh/MetaFGNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"fine-grained-visual-categorization-using-meta","repo_url":"https://github.com/YabinZhang1994/MetaFGNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"fine-grained-visual-categorization","task_name":"Fine-Grained Visual Categorization"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-dib-10k","task":"Fine-Grained Image Classification","dataset":"DIB-10K","model":"MetaFGNet","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"0.87"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.10916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.10916"}},"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/YBZh/MetaFGNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YabinZhang1994/MetaFGNet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":9},"by_repo_kind":{"listed":{"samples":10,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"YBZh/MetaFGNet","repo_kind":"listed","path":"MetaFGNet_with_Sample_Selection/models/resnet.py","file_url":"https://github.com/YBZh/MetaFGNet/blob/HEAD/MetaFGNet_with_Sample_Selection/models/resnet.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":"fac5364e2f53c6db"}},{"code_sha256_prefix":"4d3faaaa1c706b0b","entry":"accuracy","repo":"YBZh/MetaFGNet","repo_kind":"listed","path":"Fine_tune_for_final_results/trainer.py","file_url":"https://github.com/YBZh/MetaFGNet/blob/HEAD/Fine_tune_for_final_results/trainer.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":"4d3faaaa1c706b0b"}},{"code_sha256_prefix":"6dab2ac606867db8","entry":"resnet18","repo":"YBZh/MetaFGNet","repo_kind":"listed","path":"MetaFGNet_with_Sample_Selection/models/resnet.py","file_url":"https://github.com/YBZh/MetaFGNet/blob/HEAD/MetaFGNet_with_Sample_Selection/models/resnet.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":"6dab2ac606867db8"}},{"code_sha256_prefix":"58517e0806194b94","entry":"resnet18","repo":"YBZh/MetaFGNet","repo_kind":"listed","path":"Fine_tune_for_final_results/models/resnet.py","file_url":"https://github.com/YBZh/MetaFGNet/blob/HEAD/Fine_tune_for_final_results/models/resnet.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":"58517e0806194b94"}},{"code_sha256_prefix":"e790c0ef6a02aa43","entry":"resnet18","repo":"YBZh/MetaFGNet","repo_kind":"listed","path":"L_Bird_pretrain/models/resnet.py","file_url":"https://github.com/YBZh/MetaFGNet/blob/HEAD/L_Bird_pretrain/models/resnet.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":"e790c0ef6a02aa43"}},{"code_sha256_prefix":"0b2e2b5913407728","entry":"resnet34","repo":"YBZh/MetaFGNet","repo_kind":"listed","path":"MetaFGNet_with_Sample_Selection/models/resnet.py","file_url":"https://github.com/YBZh/MetaFGNet/blob/HEAD/MetaFGNet_with_Sample_Selection/models/resnet.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":"0b2e2b5913407728"}},{"code_sha256_prefix":"74fa8688ee93235c","entry":"resnet34","repo":"YBZh/MetaFGNet","repo_kind":"listed","path":"MetaFGNet_without_Sample_Selection/models/resnet.py","file_url":"https://github.com/YBZh/MetaFGNet/blob/HEAD/MetaFGNet_without_Sample_Selection/models/resnet.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":"74fa8688ee93235c"}},{"code_sha256_prefix":"49b1a02c47687245","entry":"resnet34","repo":"YBZh/MetaFGNet","repo_kind":"listed","path":"Fine_tune_for_final_results/models/resnet.py","file_url":"https://github.com/YBZh/MetaFGNet/blob/HEAD/Fine_tune_for_final_results/models/resnet.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":"49b1a02c47687245"}},{"code_sha256_prefix":"73229611b942958f","entry":"resnet34","repo":"YBZh/MetaFGNet","repo_kind":"listed","path":"L_Bird_pretrain/models/resnet.py","file_url":"https://github.com/YBZh/MetaFGNet/blob/HEAD/L_Bird_pretrain/models/resnet.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":"73229611b942958f"}},{"code_sha256_prefix":"e4fc07f10cfe1e9b","entry":"validate","repo":"YBZh/MetaFGNet","repo_kind":"listed","path":"Fine_tune_for_final_results/trainer.py","file_url":"https://github.com/YBZh/MetaFGNet/blob/HEAD/Fine_tune_for_final_results/trainer.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":"e4fc07f10cfe1e9b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}