{"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/expediting-large-scale-vision-transformer-for","title":"Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning","arxiv_id":"2210.01035","date":"2022-10-03","proceeding":null,"authors":["Weicong Liang","Yuhui Yuan","Henghui Ding","Xiao Luo","WeiHong Lin","Ding Jia","Zheng Zhang","Chao Zhang","Han Hu"],"abstract":"Vision transformers have recently achieved competitive results across various vision tasks but still suffer from heavy computation costs when processing a large number of tokens. Many advanced approaches have been developed to reduce the total number of tokens in large-scale vision transformers, especially for image classification tasks. Typically, they select a small group of essential tokens according to their relevance with the class token, then fine-tune the weights of the vision transformer. Such fine-tuning is less practical for dense prediction due to the much heavier computation and GPU memory cost than image classification. In this paper, we focus on a more challenging problem, i.e., accelerating large-scale vision transformers for dense prediction without any additional re-training or fine-tuning. In response to the fact that high-resolution representations are necessary for dense prediction, we present two non-parametric operators, a token clustering layer to decrease the number of tokens and a token reconstruction layer to increase the number of tokens. The following steps are performed to achieve this: (i) we use the token clustering layer to cluster the neighboring tokens together, resulting in low-resolution representations that maintain the spatial structures; (ii) we apply the following transformer layers only to these low-resolution representations or clustered tokens; and (iii) we use the token reconstruction layer to re-create the high-resolution representations from the refined low-resolution representations. The results obtained by our method are promising on five dense prediction tasks, including object detection, semantic segmentation, panoptic segmentation, instance segmentation, and depth estimation.","url_abs":"https://arxiv.org/abs/2210.01035v1","url_pdf":"https://arxiv.org/pdf/2210.01035v1.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":"expediting-large-scale-vision-transformer-for","repo_url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DINO","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"expediting-large-scale-vision-transformer-for","repo_url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DPT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"expediting-large-scale-vision-transformer-for","repo_url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-Segmenter","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"expediting-large-scale-vision-transformer-for","repo_url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-SWAG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.01035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01035"}},"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/Expedit-LargeScale-Vision-Transformer/Expedit-DPT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-SWAG","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DINO","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-Segmenter","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"8d4e5ab503856d09","entry":"apply_min_size","repo":"Expedit-LargeScale-Vision-Transformer/Expedit-DPT","repo_kind":"official","path":"dpt/transforms.py","file_url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DPT/blob/HEAD/dpt/transforms.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d4e5ab503856d09"}},{"code_sha256_prefix":"1c094193a4506a40","entry":"get_activation","repo":"Expedit-LargeScale-Vision-Transformer/Expedit-DPT","repo_kind":"official","path":"dpt/evit.py","file_url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DPT/blob/HEAD/dpt/evit.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c094193a4506a40"}},{"code_sha256_prefix":"a552c8f30bbe3f97","entry":"get_attention","repo":"Expedit-LargeScale-Vision-Transformer/Expedit-DPT","repo_kind":"official","path":"dpt/vit.py","file_url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DPT/blob/HEAD/dpt/vit.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a552c8f30bbe3f97"}},{"code_sha256_prefix":"0f6587dd0ee20c03","entry":"get_mean_attention_map","repo":"Expedit-LargeScale-Vision-Transformer/Expedit-DPT","repo_kind":"official","path":"dpt/vit.py","file_url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DPT/blob/HEAD/dpt/vit.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f6587dd0ee20c03"}},{"code_sha256_prefix":"348cb9ca5bb1dc15","entry":"get_aspect_ratio","repo":"Expedit-LargeScale-Vision-Transformer/Expedit-DPT","repo_kind":"official","path":"dpt/evit.py","file_url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DPT/blob/HEAD/dpt/evit.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"348cb9ca5bb1dc15"}},{"code_sha256_prefix":"6d02446a8bd47021","entry":"naive_unpool","repo":"Expedit-LargeScale-Vision-Transformer/Expedit-DPT","repo_kind":"official","path":"dpt/reconstruction.py","file_url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DPT/blob/HEAD/dpt/reconstruction.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d02446a8bd47021"}},{"code_sha256_prefix":"65e23d3e3337a16b","entry":"reshape_as_aspect_ratio","repo":"Expedit-LargeScale-Vision-Transformer/Expedit-DPT","repo_kind":"official","path":"dpt/evit.py","file_url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DPT/blob/HEAD/dpt/evit.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65e23d3e3337a16b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}