{"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/dynamic-grained-encoder-for-vision-1","title":"Dynamic Grained Encoder for Vision Transformers","arxiv_id":"2301.03831","date":"2023-01-10","proceeding":"NeurIPS 2021 12","authors":["Lin Song","Songyang Zhang","Songtao Liu","Zeming Li","Xuming He","Hongbin Sun","Jian Sun","Nanning Zheng"],"abstract":"Transformers, the de-facto standard for language modeling, have been recently applied for vision tasks. This paper introduces sparse queries for vision transformers to exploit the intrinsic spatial redundancy of natural images and save computational costs. Specifically, we propose a Dynamic Grained Encoder for vision transformers, which can adaptively assign a suitable number of queries to each spatial region. Thus it achieves a fine-grained representation in discriminative regions while keeping high efficiency. Besides, the dynamic grained encoder is compatible with most vision transformer frameworks. Without bells and whistles, our encoder allows the state-of-the-art vision transformers to reduce computational complexity by 40%-60% while maintaining comparable performance on image classification. Extensive experiments on object detection and segmentation further demonstrate the generalizability of our approach. Code is available at https://github.com/StevenGrove/vtpack.","url_abs":"https://arxiv.org/abs/2301.03831v1","url_pdf":"https://arxiv.org/pdf/2301.03831v1.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":"dynamic-grained-encoder-for-vision-1","repo_url":"https://github.com/stevengrove/vtpack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"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":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.03831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.03831"}},"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/stevengrove/vtpack","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"9153241c4331eb1a","entry":"build_dataset","repo":"stevengrove/vtpack","repo_kind":"official","path":"vtpack/engine/datasets.py","file_url":"https://github.com/stevengrove/vtpack/blob/HEAD/vtpack/engine/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":false,"mcp_get_code":{"code_sha256":"9153241c4331eb1a"}},{"code_sha256_prefix":"3bc74137ab36aa79","entry":"build_transform","repo":"stevengrove/vtpack","repo_kind":"official","path":"vtpack/engine/datasets.py","file_url":"https://github.com/stevengrove/vtpack/blob/HEAD/vtpack/engine/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":false,"mcp_get_code":{"code_sha256":"3bc74137ab36aa79"}},{"code_sha256_prefix":"2a5305120e29e949","entry":"evaluate","repo":"stevengrove/vtpack","repo_kind":"official","path":"vtpack/engine/engine.py","file_url":"https://github.com/stevengrove/vtpack/blob/HEAD/vtpack/engine/engine.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":false,"mcp_get_code":{"code_sha256":"2a5305120e29e949"}},{"code_sha256_prefix":"4281f557cdf8a1be","entry":"grained_sample_compress_dense","repo":"stevengrove/vtpack","repo_kind":"official","path":"vtpack/layers/grained_sample.py","file_url":"https://github.com/stevengrove/vtpack/blob/HEAD/vtpack/layers/grained_sample.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":false,"mcp_get_code":{"code_sha256":"4281f557cdf8a1be"}},{"code_sha256_prefix":"95ded5901d658b8a","entry":"grained_sample_decompress_dense","repo":"stevengrove/vtpack","repo_kind":"official","path":"vtpack/layers/grained_sample.py","file_url":"https://github.com/stevengrove/vtpack/blob/HEAD/vtpack/layers/grained_sample.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":false,"mcp_get_code":{"code_sha256":"95ded5901d658b8a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}