{"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/self-adapting-large-visual-language-models-to","title":"Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities","arxiv_id":"2403.04908","date":"2024-03-07","proceeding":null,"authors":["Kaiwen Cai","Zhekai Duan","Gaowen Liu","Charles Fleming","Chris Xiaoxuan Lu"],"abstract":"Recent advancements in Vision-Language (VL) models have sparked interest in their deployment on edge devices, yet challenges in handling diverse visual modalities, manual annotation, and computational constraints remain. We introduce EdgeVL, a novel framework that bridges this gap by seamlessly integrating dual-modality knowledge distillation and quantization-aware contrastive learning. This approach enables the adaptation of large VL models, like CLIP, for efficient use with both RGB and non-RGB images on resource-limited devices without the need for manual annotations. EdgeVL not only transfers visual language alignment capabilities to compact models but also maintains feature quality post-quantization, significantly enhancing open-vocabulary classification performance across various visual modalities. Our work represents the first systematic effort to adapt large VL models for edge deployment, showcasing up to 15.4% accuracy improvements on multiple datasets and up to 93-fold reduction in model size.","url_abs":"https://arxiv.org/abs/2403.04908v3","url_pdf":"https://arxiv.org/pdf/2403.04908v3.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":"self-adapting-large-visual-language-models-to","repo_url":"https://github.com/ramdrop/edgevl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.04908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04908"}},"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/ramdrop/edgevl","reach":{"status":"ok"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"9cf1bb83d295862a","entry":"convert_string","repo":"ramdrop/edgevl","repo_kind":"official","path":"export_clip_labels.py","file_url":"https://github.com/ramdrop/edgevl/blob/HEAD/export_clip_labels.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9cf1bb83d295862a"}},{"code_sha256_prefix":"b978089efda230ec","entry":"convert_string","repo":"ramdrop/edgevl","repo_kind":"official","path":"dataset/scannet/scannet.py","file_url":"https://github.com/ramdrop/edgevl/blob/HEAD/dataset/scannet/scannet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b978089efda230ec"}},{"code_sha256_prefix":"cf82c8be3014b689","entry":"determine_prefix","repo":"ramdrop/edgevl","repo_kind":"official","path":"export_clip_labels.py","file_url":"https://github.com/ramdrop/edgevl/blob/HEAD/export_clip_labels.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cf82c8be3014b689"}},{"code_sha256_prefix":"63423ca6c9f8cb47","entry":"remove_spaces_around_slash","repo":"ramdrop/edgevl","repo_kind":"official","path":"dataset/scannet/scannet.py","file_url":"https://github.com/ramdrop/edgevl/blob/HEAD/dataset/scannet/scannet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"63423ca6c9f8cb47"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}