{"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/upop-unified-and-progressive-pruning-for","title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","arxiv_id":"2301.13741","date":"2023-01-31","proceeding":null,"authors":["Dachuan Shi","Chaofan Tao","Ying Jin","Zhendong Yang","Chun Yuan","Jiaqi Wang"],"abstract":"Real-world data contains a vast amount of multimodal information, among which vision and language are the two most representative modalities. Moreover, increasingly heavier models, \\textit{e}.\\textit{g}., Transformers, have attracted the attention of researchers to model compression. However, how to compress multimodal models, especially vison-language Transformers, is still under-explored. This paper proposes the \\textbf{U}nified and \\textbf{P}r\\textbf{o}gressive \\textbf{P}runing (\\textbf{\\emph{UPop}}) as a universal vison-language Transformer compression framework, which incorporates 1) unifiedly searching multimodal subnets in a continuous optimization space from the original model, which enables automatic assignment of pruning ratios among compressible modalities and structures; 2) progressively searching and retraining the subnet, which maintains convergence between the search and retrain to attain higher compression ratios. Experiments on various tasks, datasets, and model architectures demonstrate the effectiveness and versatility of the proposed UPop framework. The code is available at https://github.com/sdc17/UPop.","url_abs":"https://arxiv.org/abs/2301.13741v3","url_pdf":"https://arxiv.org/pdf/2301.13741v3.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":"upop-unified-and-progressive-pruning-for","repo_url":"https://github.com/sdc17/upop","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"upop-unified-and-progressive-pruning-for","repo_url":"https://github.com/sdc17/crossget","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"image-text-retrieval","task_name":"Image-text Retrieval"},{"task_slug":"image-to-text-retrieval","task_name":"Image-to-Text Retrieval"},{"task_slug":"model-compression","task_name":"Model Compression"},{"task_slug":"network-pruning","task_name":"Network Pruning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2301.13741","atlas_url":"https://app.syntology.ai/?focus=2301.13741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13741"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/sdc17/UPop","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sdc17/crossget","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sdc17/upop","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":1,"ran":0,"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":"c5ba355bd1c09ea4","entry":"TokenReduction","repo":"sdc17/crossget","repo_kind":"listed","path":"LLaVA/llava/model/reducer.py","file_url":"https://github.com/sdc17/crossget/blob/HEAD/LLaVA/llava/model/reducer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c5ba355bd1c09ea4"}},{"code_sha256_prefix":"f1ad8af135d8bc70","entry":"update_alpha_parameters","repo":"sdc17/upop","repo_kind":"official","path":"compress_retrieval.py","file_url":"https://github.com/sdc17/upop/blob/HEAD/compress_retrieval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f1ad8af135d8bc70"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}