{"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/vicinity-vision-transformer","title":"Vicinity Vision Transformer","arxiv_id":"2206.10552","date":"2022-06-21","proceeding":null,"authors":["Weixuan Sun","Zhen Qin","Hui Deng","Jianyuan Wang","Yi Zhang","Kaihao Zhang","Nick Barnes","Stan Birchfield","Lingpeng Kong","Yiran Zhong"],"abstract":"Vision transformers have shown great success on numerous computer vision tasks. However, its central component, softmax attention, prohibits vision transformers from scaling up to high-resolution images, due to both the computational complexity and memory footprint being quadratic. Although linear attention was introduced in natural language processing (NLP) tasks to mitigate a similar issue, directly applying existing linear attention to vision transformers may not lead to satisfactory results. We investigate this problem and find that computer vision tasks focus more on local information compared with NLP tasks. Based on this observation, we present a Vicinity Attention that introduces a locality bias to vision transformers with linear complexity. Specifically, for each image patch, we adjust its attention weight based on its 2D Manhattan distance measured by its neighbouring patches. In this case, the neighbouring patches will receive stronger attention than far-away patches. Moreover, since our Vicinity Attention requires the token length to be much larger than the feature dimension to show its efficiency advantages, we further propose a new Vicinity Vision Transformer (VVT) structure to reduce the feature dimension without degenerating the accuracy. We perform extensive experiments on the CIFAR100, ImageNet1K, and ADE20K datasets to validate the effectiveness of our method. Our method has a slower growth rate of GFlops than previous transformer-based and convolution-based networks when the input resolution increases. In particular, our approach achieves state-of-the-art image classification accuracy with 50% fewer parameters than previous methods.","url_abs":"https://arxiv.org/abs/2206.10552v2","url_pdf":"https://arxiv.org/pdf/2206.10552v2.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":"vicinity-vision-transformer","repo_url":"https://github.com/opennlplab/vicinity-vision-transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"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":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"VVT-L (384 res)","rank_in_archive_order":297,"of":1060,"metrics":{"GFLOPs":"31.8","Number of params":"61.8M","Top 1 Accuracy":"84.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"VVT-L (224 res)","rank_in_archive_order":357,"of":1060,"metrics":{"GFLOPs":"10.8","Number of params":"61.8M","Top 1 Accuracy":"84.1%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.10552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.10552"}},"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/opennlplab/vicinity-vision-transformer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"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":"927e684e71ca3ee9","entry":"compute_rollout_attention","repo":"opennlplab/vicinity-vision-transformer","repo_kind":"official","path":"classification/pvt_v2.py","file_url":"https://github.com/opennlplab/vicinity-vision-transformer/blob/HEAD/classification/pvt_v2.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"927e684e71ca3ee9"}},{"code_sha256_prefix":"3bc74137ab36aa79","entry":"build_transform","repo":"opennlplab/vicinity-vision-transformer","repo_kind":"official","path":"classification/datasets.py","file_url":"https://github.com/opennlplab/vicinity-vision-transformer/blob/HEAD/classification/datasets.py","link_basis":"harvester_set","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":"3bc74137ab36aa79"}},{"code_sha256_prefix":"8f7ece6602227d86","entry":"fra_flops","repo":"opennlplab/vicinity-vision-transformer","repo_kind":"official","path":"classification/get_flops.py","file_url":"https://github.com/opennlplab/vicinity-vision-transformer/blob/HEAD/classification/get_flops.py","link_basis":"harvester_set","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":"8f7ece6602227d86"}},{"code_sha256_prefix":"90e0b9db0ae2a681","entry":"li_sra_flops","repo":"opennlplab/vicinity-vision-transformer","repo_kind":"official","path":"classification/get_flops.py","file_url":"https://github.com/opennlplab/vicinity-vision-transformer/blob/HEAD/classification/get_flops.py","link_basis":"harvester_set","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":"90e0b9db0ae2a681"}},{"code_sha256_prefix":"5eb28a11cf629463","entry":"sra_flops","repo":"opennlplab/vicinity-vision-transformer","repo_kind":"official","path":"classification/get_flops.py","file_url":"https://github.com/opennlplab/vicinity-vision-transformer/blob/HEAD/classification/get_flops.py","link_basis":"harvester_set","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":"5eb28a11cf629463"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}