{"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/pre-trained-vision-and-language-transformers","title":"Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners","arxiv_id":"2404.02117","date":"2024-04-02","proceeding":"CVPR 2024 1","authors":["Keon-Hee Park","Kyungwoo Song","Gyeong-Moon Park"],"abstract":"Few-Shot Class Incremental Learning (FSCIL) is a task that requires a model to learn new classes incrementally without forgetting when only a few samples for each class are given. FSCIL encounters two significant challenges: catastrophic forgetting and overfitting, and these challenges have driven prior studies to primarily rely on shallow models, such as ResNet-18. Even though their limited capacity can mitigate both forgetting and overfitting issues, it leads to inadequate knowledge transfer during few-shot incremental sessions. In this paper, we argue that large models such as vision and language transformers pre-trained on large datasets can be excellent few-shot incremental learners. To this end, we propose a novel FSCIL framework called PriViLege, Pre-trained Vision and Language transformers with prompting functions and knowledge distillation. Our framework effectively addresses the challenges of catastrophic forgetting and overfitting in large models through new pre-trained knowledge tuning (PKT) and two losses: entropy-based divergence loss and semantic knowledge distillation loss. Experimental results show that the proposed PriViLege significantly outperforms the existing state-of-the-art methods with a large margin, e.g., +9.38% in CUB200, +20.58% in CIFAR-100, and +13.36% in miniImageNet. Our implementation code is available at https://github.com/KHU-AGI/PriViLege.","url_abs":"https://arxiv.org/abs/2404.02117v1","url_pdf":"https://arxiv.org/pdf/2404.02117v1.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":"pre-trained-vision-and-language-transformers","repo_url":"https://github.com/khu-agi/privilege","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"few-shot-class-incremental-learning","task_name":"Few-Shot Class-Incremental Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-class-incremental-learning-on-cifar","task":"Few-Shot Class-Incremental Learning","dataset":"CIFAR-100","model":"PriViLege","rank_in_archive_order":1,"of":11,"metrics":{"Average Accuracy":"88.08","Last Accuracy":"86.06"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-class-incremental-learning-on-cub","task":"Few-Shot Class-Incremental Learning","dataset":"CUB-200-2011","model":"PriViLege (ViT-L)","rank_in_archive_order":2,"of":6,"metrics":{"Average Accuracy":"79.20","Last Accuracy ":"76.43"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-class-incremental-learning-on-cub","task":"Few-Shot Class-Incremental Learning","dataset":"CUB-200-2011","model":"PriViLege","rank_in_archive_order":4,"of":6,"metrics":{"Average Accuracy":"77.50","Last Accuracy ":"75.08"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-class-incremental-learning-on-mini","task":"Few-Shot Class-Incremental Learning","dataset":"mini-Imagenet","model":"PriViLege","rank_in_archive_order":2,"of":12,"metrics":{"Average Accuracy":"95.27","Last Accuracy ":"94.10"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2404.02117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02117"}},"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/KHU-AGI/PriViLege","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"ran":8,"unverified":2},"by_repo_kind":{"official":{"samples":14,"ran":12,"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":"d9def42110729a85","entry":"conv1x1","repo":"KHU-AGI/PriViLege","repo_kind":"official","path":"models/resnet18_encoder.py","file_url":"https://github.com/KHU-AGI/PriViLege/blob/HEAD/models/resnet18_encoder.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":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"KHU-AGI/PriViLege","repo_kind":"official","path":"models/resnet18_encoder.py","file_url":"https://github.com/KHU-AGI/PriViLege/blob/HEAD/models/resnet18_encoder.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":"160bb14bd76201b4"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"KHU-AGI/PriViLege","repo_kind":"official","path":"models/resnet20_cifar.py","file_url":"https://github.com/KHU-AGI/PriViLege/blob/HEAD/models/resnet20_cifar.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":"ce5f4e253ac16c0b","entry":"count_acc","repo":"KHU-AGI/PriViLege","repo_kind":"official","path":"utils.py","file_url":"https://github.com/KHU-AGI/PriViLege/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ce5f4e253ac16c0b"}},{"code_sha256_prefix":"9f5eb9c8c810bac9","entry":"ensure_tensor","repo":"KHU-AGI/PriViLege","repo_kind":"official","path":"models/rotated_modules.py","file_url":"https://github.com/KHU-AGI/PriViLege/blob/HEAD/models/rotated_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f5eb9c8c810bac9"}},{"code_sha256_prefix":"f7bd6331d1ecd9d4","entry":"im2col","repo":"KHU-AGI/PriViLege","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/KHU-AGI/PriViLege/blob/HEAD/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f7bd6331d1ecd9d4"}},{"code_sha256_prefix":"4bf8c74e32ceacec","entry":"im2col_from_conv","repo":"KHU-AGI/PriViLege","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/KHU-AGI/PriViLege/blob/HEAD/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4bf8c74e32ceacec"}},{"code_sha256_prefix":"c6ec173f19f5c34d","entry":"interpolate_pos_embed","repo":"KHU-AGI/PriViLege","repo_kind":"official","path":"models/vision_transformer.py","file_url":"https://github.com/KHU-AGI/PriViLege/blob/HEAD/models/vision_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6ec173f19f5c34d"}},{"code_sha256_prefix":"422a6083ee9c106d","entry":"load_state_dict_from_url","repo":"KHU-AGI/PriViLege","repo_kind":"official","path":"models/resnet18_encoder.py","file_url":"https://github.com/KHU-AGI/PriViLege/blob/HEAD/models/resnet18_encoder.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"422a6083ee9c106d"}},{"code_sha256_prefix":"8ca1b5efa4e118ad","entry":"same_device","repo":"KHU-AGI/PriViLege","repo_kind":"official","path":"models/rotated_modules.py","file_url":"https://github.com/KHU-AGI/PriViLege/blob/HEAD/models/rotated_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ca1b5efa4e118ad"}},{"code_sha256_prefix":"8327880f0b76f9db","entry":"set_gpu","repo":"KHU-AGI/PriViLege","repo_kind":"official","path":"utils.py","file_url":"https://github.com/KHU-AGI/PriViLege/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8327880f0b76f9db"}},{"code_sha256_prefix":"6926d6120740537c","entry":"set_grad","repo":"KHU-AGI/PriViLege","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/KHU-AGI/PriViLege/blob/HEAD/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6926d6120740537c"}},{"code_sha256_prefix":"6af93d8743b553e5","entry":"identify_importance","repo":"KHU-AGI/PriViLege","repo_kind":"official","path":"utils.py","file_url":"https://github.com/KHU-AGI/PriViLege/blob/HEAD/utils.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":"6af93d8743b553e5"}},{"code_sha256_prefix":"02c87c5ca25b0326","entry":"switch_module","repo":"KHU-AGI/PriViLege","repo_kind":"official","path":"models/switch_module.py","file_url":"https://github.com/KHU-AGI/PriViLege/blob/HEAD/models/switch_module.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":"02c87c5ca25b0326"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}