{"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/gtp-vit-efficient-vision-transformers-via","title":"GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation","arxiv_id":"2311.03035","date":"2023-11-06","proceeding":null,"authors":["Xuwei Xu","Sen Wang","Yudong Chen","Yanping Zheng","Zhewei Wei","Jiajun Liu"],"abstract":"Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their deployments on resource-constrained devices remain challenging due to high computational demands. To expedite pre-trained ViTs, token pruning and token merging approaches have been developed, which aim at reducing the number of tokens involved in the computation. However, these methods still have some limitations, such as image information loss from pruned tokens and inefficiency in the token-matching process. In this paper, we introduce a novel Graph-based Token Propagation (GTP) method to resolve the challenge of balancing model efficiency and information preservation for efficient ViTs. Inspired by graph summarization algorithms, GTP meticulously propagates less significant tokens' information to spatially and semantically connected tokens that are of greater importance. Consequently, the remaining few tokens serve as a summarization of the entire token graph, allowing the method to reduce computational complexity while preserving essential information of eliminated tokens. Combined with an innovative token selection strategy, GTP can efficiently identify image tokens to be propagated. Extensive experiments have validated GTP's effectiveness, demonstrating both efficiency and performance improvements. Specifically, GTP decreases the computational complexity of both DeiT-S and DeiT-B by up to 26% with only a minimal 0.3% accuracy drop on ImageNet-1K without finetuning, and remarkably surpasses the state-of-the-art token merging method on various backbones at an even faster inference speed. The source code is available at https://github.com/Ackesnal/GTP-ViT.","url_abs":"https://arxiv.org/abs/2311.03035v2","url_pdf":"https://arxiv.org/pdf/2311.03035v2.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":"gtp-vit-efficient-vision-transformers-via","repo_url":"https://github.com/ackesnal/gtp-vit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"efficient-vits","task_name":"Efficient ViTs"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"GTP-ViT-B-Patch8/P20","rank_in_archive_order":191,"of":1060,"metrics":{"Top 1 Accuracy":"85.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"GTP-EVA-L/P8","rank_in_archive_order":229,"of":1060,"metrics":{"Top 1 Accuracy":"85.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"GTP-ViT-L/P8","rank_in_archive_order":393,"of":1060,"metrics":{"Top 1 Accuracy":"83.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"GTP-LV-ViT-M/P8","rank_in_archive_order":492,"of":1060,"metrics":{"GFLOPs":"8","Top 1 Accuracy":"82.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"GTP-LV-ViT-S/P8","rank_in_archive_order":592,"of":1060,"metrics":{"GFLOPs":"4.8","Top 1 Accuracy":"81.9%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"GTP-DeiT-B/P8","rank_in_archive_order":630,"of":1060,"metrics":{"GFLOPs":"13.1","Top 1 Accuracy":"81.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"GTP-DeiT-S/P8","rank_in_archive_order":750,"of":1060,"metrics":{"GFLOPs":"3.4","Top 1 Accuracy":"79.5%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.03035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03035"}},"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/ackesnal/gtp-vit","reach":null}],"summary":{"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":"fc2f6c8685c520eb","entry":"select","repo":"ackesnal/gtp-vit","repo_kind":"official","path":"models_v3.py","file_url":"https://github.com/ackesnal/gtp-vit/blob/HEAD/models_v3.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fc2f6c8685c520eb"}},{"code_sha256_prefix":"0e95f70efaf7910b","entry":"propagate","repo":"ackesnal/gtp-vit","repo_kind":"official","path":"models_v3.py","file_url":"https://github.com/ackesnal/gtp-vit/blob/HEAD/models_v3.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0e95f70efaf7910b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}