{"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/hiera-a-hierarchical-vision-transformer","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","arxiv_id":"2306.00989","date":"2023-06-01","proceeding":null,"authors":["Chaitanya Ryali","Yuan-Ting Hu","Daniel Bolya","Chen Wei","Haoqi Fan","Po-Yao Huang","Vaibhav Aggarwal","Arkabandhu Chowdhury","Omid Poursaeed","Judy Hoffman","Jitendra Malik","Yanghao Li","Christoph Feichtenhofer"],"abstract":"Modern hierarchical vision transformers have added several vision-specific components in the pursuit of supervised classification performance. While these components lead to effective accuracies and attractive FLOP counts, the added complexity actually makes these transformers slower than their vanilla ViT counterparts. In this paper, we argue that this additional bulk is unnecessary. By pretraining with a strong visual pretext task (MAE), we can strip out all the bells-and-whistles from a state-of-the-art multi-stage vision transformer without losing accuracy. In the process, we create Hiera, an extremely simple hierarchical vision transformer that is more accurate than previous models while being significantly faster both at inference and during training. We evaluate Hiera on a variety of tasks for image and video recognition. Our code and models are available at https://github.com/facebookresearch/hiera.","url_abs":"https://arxiv.org/abs/2306.00989v1","url_pdf":"https://arxiv.org/pdf/2306.00989v1.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":"hiera-a-hierarchical-vision-transformer","repo_url":"https://github.com/facebookresearch/hiera","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"hiera-a-hierarchical-vision-transformer","repo_url":"https://github.com/huggingface/pytorch-image-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"hiera-a-hierarchical-vision-transformer","repo_url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/hiera","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"hiera-a-hierarchical-vision-transformer","repo_url":"https://gitlab.com/birder/birder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition-in-videos-2","task_name":"Action Recognition In Videos"},{"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":"video-recognition","task_name":"Video Recognition"}],"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":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"Hiera-H (no extra data)","rank_in_archive_order":31,"of":207,"metrics":{"Acc@1":"87.8"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"Hiera-H (no extra data)","rank_in_archive_order":18,"of":65,"metrics":{"Top-1 Accuracy":"88.8"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-700","task":"Action Classification","dataset":"Kinetics-700","model":"Hiera-H (no extra data)","rank_in_archive_order":11,"of":36,"metrics":{"Top-1 Accuracy":"81.1"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-on-ava-v2-2","task":"Action Recognition","dataset":"AVA v2.2","model":"Hiera-H (K700 PT+FT)","rank_in_archive_order":2,"of":38,"metrics":{"mAP":"43.3"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"Hiera-L (no extra data)","rank_in_archive_order":7,"of":123,"metrics":{"Top-1 Accuracy":"76.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"Hiera-H","rank_in_archive_order":115,"of":1060,"metrics":{"Top 1 Accuracy":"86.9%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-places365-standard","task":"Image Classification","dataset":"Places365-Standard","model":"Hiera-H (448px)","rank_in_archive_order":2,"of":4,"metrics":{"Top 1 Accuracy":"60.6"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-inaturalist","task":"Image Classification","dataset":"iNaturalist","model":"Hiera-H (448px)","rank_in_archive_order":2,"of":19,"metrics":{"Top 1 Accuracy":"83.8"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"Hiera-H (448px)","rank_in_archive_order":6,"of":60,"metrics":{"Top-1 Accuracy":"87.3%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-inaturalist-2019","task":"Image Classification","dataset":"iNaturalist 2019","model":"Hiera-H (448px)","rank_in_archive_order":1,"of":22,"metrics":{"Top-1 Accuracy":"88.5"},"uses_additional_data":true},{"leaderboard":"/sota/instance-segmentation-on-coco-minival","task":"Instance Segmentation","dataset":"COCO minival","model":"Heira-L","rank_in_archive_order":34,"of":93,"metrics":{"mask AP":"48.6"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"Hiera-L","rank_in_archive_order":52,"of":220,"metrics":{"box AP":"55"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.00989","atlas_url":"https://app.syntology.ai/?focus=2306.00989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00989"}},"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/facebookresearch/hiera","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/pytorch-image-models","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/hiera","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://gitlab.com/birder/birder","reach":null}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"815d1d88e2fbc27f","entry":"apply_fusion_head","repo":"facebookresearch/hiera","repo_kind":"official","path":"hiera/hiera_mae.py","file_url":"https://github.com/facebookresearch/hiera/blob/HEAD/hiera/hiera_mae.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":"815d1d88e2fbc27f"}},{"code_sha256_prefix":"b160eae20550159c","entry":"benchmark","repo":"facebookresearch/hiera","repo_kind":"official","path":"hiera/benchmarking.py","file_url":"https://github.com/facebookresearch/hiera/blob/HEAD/hiera/benchmarking.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":"b160eae20550159c"}},{"code_sha256_prefix":"8a833cf7d1d043a1","entry":"conv_nd","repo":"facebookresearch/hiera","repo_kind":"official","path":"hiera/hiera_utils.py","file_url":"https://github.com/facebookresearch/hiera/blob/HEAD/hiera/hiera_utils.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":"8a833cf7d1d043a1"}},{"code_sha256_prefix":"8b6a5042461e32ae","entry":"do_pool","repo":"facebookresearch/hiera","repo_kind":"official","path":"hiera/hiera_utils.py","file_url":"https://github.com/facebookresearch/hiera/blob/HEAD/hiera/hiera_utils.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":"8b6a5042461e32ae"}},{"code_sha256_prefix":"5a74f72c4653f308","entry":"has_config","repo":"facebookresearch/hiera","repo_kind":"official","path":"hiera/hfhub.py","file_url":"https://github.com/facebookresearch/hiera/blob/HEAD/hiera/hfhub.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":"5a74f72c4653f308"}},{"code_sha256_prefix":"85ff40001ae9f4c3","entry":"pretrained_model","repo":"facebookresearch/hiera","repo_kind":"official","path":"hiera/hiera_utils.py","file_url":"https://github.com/facebookresearch/hiera/blob/HEAD/hiera/hiera_utils.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":"85ff40001ae9f4c3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}