{"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/parameter-efficient-long-tailed-recognition","title":"Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts","arxiv_id":"2309.10019","date":"2023-09-18","proceeding":null,"authors":["Jiang-Xin Shi","Tong Wei","Zhi Zhou","Jie-Jing Shao","Xin-Yan Han","Yu-Feng Li"],"abstract":"The fine-tuning paradigm in addressing long-tail learning tasks has sparked significant interest since the emergence of foundation models. Nonetheless, how fine-tuning impacts performance in long-tail learning was not explicitly quantified. In this paper, we disclose that heavy fine-tuning may even lead to non-negligible performance deterioration on tail classes, and lightweight fine-tuning is more effective. The reason is attributed to inconsistent class conditions caused by heavy fine-tuning. With the observation above, we develop a low-complexity and accurate long-tail learning algorithms LIFT with the goal of facilitating fast prediction and compact models by adaptive lightweight fine-tuning. Experiments clearly verify that both the training time and the learned parameters are significantly reduced with more accurate predictive performance compared with state-of-the-art approaches. The implementation code is available at https://github.com/shijxcs/LIFT.","url_abs":"https://arxiv.org/abs/2309.10019v3","url_pdf":"https://arxiv.org/pdf/2309.10019v3.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":"parameter-efficient-long-tailed-recognition","repo_url":"https://github.com/shijxcs/lift","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"},{"task_slug":"long-tail-learning-with-class-descriptors","task_name":"Long-tail learning with class descriptors"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=10)","model":"LIFT (ViT-B/16, ImageNet-21K pre-training)","rank_in_archive_order":1,"of":31,"metrics":{"Error Rate":"8.7"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-10","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=10)","model":"LIFT (ViT-B/16, CLIP)","rank_in_archive_order":4,"of":31,"metrics":{"Error Rate":"15.1"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=100)","model":"LIFT (ViT-B/16, ImageNet-21K pre-training)","rank_in_archive_order":2,"of":66,"metrics":{"Error Rate":"10.9"},"uses_additional_data":true},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-100","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=100)","model":"LIFT (ViT-B/16, CLIP)","rank_in_archive_order":3,"of":66,"metrics":{"Error Rate":"18.3"},"uses_additional_data":true},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-50","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=50)","model":"LIFT (ViT-B/16, ImageNet-21K pre-training)","rank_in_archive_order":1,"of":25,"metrics":{"Error Rate":"9.8"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-50","task":"Long-tail Learning","dataset":"CIFAR-100-LT (ρ=50)","model":"LIFT (ViT-B/16, CLIP)","rank_in_archive_order":4,"of":25,"metrics":{"Error Rate":"16.9"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"LIFT (ViT-L/14)","rank_in_archive_order":1,"of":69,"metrics":{"Top-1 Accuracy":"82.9"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"LIFT (ViT-B/16)","rank_in_archive_order":4,"of":69,"metrics":{"Top-1 Accuracy":"78.3"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"LIFT (ViT-L/14)","rank_in_archive_order":1,"of":29,"metrics":{"Top-1 Accuracy":"53.7"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"LIFT (ViT-B/16)","rank_in_archive_order":2,"of":29,"metrics":{"Top-1 Accuracy":"52.2"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"LIFT (ViT-L/14@336px)","rank_in_archive_order":1,"of":43,"metrics":{"Top-1 Accuracy":"87.4%"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"LIFT (ViT-L/14)","rank_in_archive_order":2,"of":43,"metrics":{"Top-1 Accuracy":"85.2%"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"LIFT (ViT-B/16)","rank_in_archive_order":5,"of":43,"metrics":{"Top-1 Accuracy":"80.4%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.10019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.10019"}},"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/shijxcs/LIFT","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shijxcs/lift","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_draft_wrong":4,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"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":8,"samples":[{"code_sha256_prefix":"152823b85e68d486","entry":"LoRA","repo":"shijxcs/lift","repo_kind":"official","path":"models/peft_modules.py","file_url":"https://github.com/shijxcs/lift/blob/HEAD/models/peft_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"152823b85e68d486"}},{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"shijxcs/LIFT","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/shijxcs/LIFT/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"4dcf06ba28983266","entry":"focal_loss","repo":"shijxcs/LIFT","repo_kind":"official","path":"utils/losses.py","file_url":"https://github.com/shijxcs/LIFT/blob/HEAD/utils/losses.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4dcf06ba28983266"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"shijxcs/LIFT","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/shijxcs/LIFT/blob/HEAD/clip/simple_tokenizer.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"shijxcs/LIFT","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/shijxcs/LIFT/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"c47aa9e5b049a11d","entry":"build_model","repo":"shijxcs/LIFT","repo_kind":"official","path":"clip/model.py","file_url":"https://github.com/shijxcs/LIFT/blob/HEAD/clip/model.py","link_basis":"harvester_set","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":"c47aa9e5b049a11d"}},{"code_sha256_prefix":"c22a78c25372b59f","entry":"load","repo":"shijxcs/LIFT","repo_kind":"official","path":"clip/clip.py","file_url":"https://github.com/shijxcs/LIFT/blob/HEAD/clip/clip.py","link_basis":"harvester_set","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":"c22a78c25372b59f"}},{"code_sha256_prefix":"3597147d80c14dc2","entry":"load_vit_to_cpu","repo":"shijxcs/LIFT","repo_kind":"official","path":"trainer.py","file_url":"https://github.com/shijxcs/LIFT/blob/HEAD/trainer.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":"3597147d80c14dc2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}