{"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/distilling-large-vision-language-model-with","title":"Distilling Large Vision-Language Model with Out-of-Distribution Generalizability","arxiv_id":"2307.03135","date":"2023-07-06","proceeding":"ICCV 2023 1","authors":["Xuanlin Li","Yunhao Fang","Minghua Liu","Zhan Ling","Zhuowen Tu","Hao Su"],"abstract":"Large vision-language models have achieved outstanding performance, but their size and computational requirements make their deployment on resource-constrained devices and time-sensitive tasks impractical. Model distillation, the process of creating smaller, faster models that maintain the performance of larger models, is a promising direction towards the solution. This paper investigates the distillation of visual representations in large teacher vision-language models into lightweight student models using a small- or mid-scale dataset. Notably, this study focuses on open-vocabulary out-of-distribution (OOD) generalization, a challenging problem that has been overlooked in previous model distillation literature. We propose two principles from vision and language modality perspectives to enhance student's OOD generalization: (1) by better imitating teacher's visual representation space, and carefully promoting better coherence in vision-language alignment with the teacher; (2) by enriching the teacher's language representations with informative and finegrained semantic attributes to effectively distinguish between different labels. We propose several metrics and conduct extensive experiments to investigate their techniques. The results demonstrate significant improvements in zero-shot and few-shot student performance on open-vocabulary out-of-distribution classification, highlighting the effectiveness of our proposed approaches. Poster: https://xuanlinli17.github.io/pdfs/iccv23_large_vlm_distillation_poster.pdf Code: https://github.com/xuanlinli17/large_vlm_distillation_ood","url_abs":"https://arxiv.org/abs/2307.03135v3","url_pdf":"https://arxiv.org/pdf/2307.03135v3.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":"distilling-large-vision-language-model-with","repo_url":"https://github.com/xuanlinli17/large_vlm_distillation_ood","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"zero-shot-image-classification","task_name":"Zero-Shot Image Classification"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"zero-shot-transfer-image-classification","task_name":"Zero-Shot Transfer Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.03135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.03135"}},"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/xuanlinli17/large_vlm_distillation_ood","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":"2a80220dabcb742a","entry":"conv1x1","repo":"xuanlinli17/large_vlm_distillation_ood","repo_kind":"official","path":"models/imagenet/resnet.py","file_url":"https://github.com/xuanlinli17/large_vlm_distillation_ood/blob/HEAD/models/imagenet/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":"2a80220dabcb742a"}},{"code_sha256_prefix":"600ff2c45e0de056","entry":"conv3x3","repo":"xuanlinli17/large_vlm_distillation_ood","repo_kind":"official","path":"models/imagenet/resnet.py","file_url":"https://github.com/xuanlinli17/large_vlm_distillation_ood/blob/HEAD/models/imagenet/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":"600ff2c45e0de056"}},{"code_sha256_prefix":"d0e6021d958f30c1","entry":"find_classes","repo":"xuanlinli17/large_vlm_distillation_ood","repo_kind":"official","path":"custom_data_loader.py","file_url":"https://github.com/xuanlinli17/large_vlm_distillation_ood/blob/HEAD/custom_data_loader.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":"d0e6021d958f30c1"}},{"code_sha256_prefix":"50afa2863ffd9fde","entry":"plot_overlap","repo":"xuanlinli17/large_vlm_distillation_ood","repo_kind":"official","path":"utils/logger.py","file_url":"https://github.com/xuanlinli17/large_vlm_distillation_ood/blob/HEAD/utils/logger.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":"50afa2863ffd9fde"}},{"code_sha256_prefix":"1d6e2edb8832d7b0","entry":"get_mean_and_std","repo":"xuanlinli17/large_vlm_distillation_ood","repo_kind":"official","path":"utils/misc.py","file_url":"https://github.com/xuanlinli17/large_vlm_distillation_ood/blob/HEAD/utils/misc.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":"1d6e2edb8832d7b0"}},{"code_sha256_prefix":"c57549f473cc2d43","entry":"resnet18","repo":"xuanlinli17/large_vlm_distillation_ood","repo_kind":"official","path":"models/imagenet/resnet.py","file_url":"https://github.com/xuanlinli17/large_vlm_distillation_ood/blob/HEAD/models/imagenet/resnet.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":"c57549f473cc2d43"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}