Papers › Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles

Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles

1 Jun 2023arXiv:2306.00989archive 2025-07-28

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

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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2306.00989")

Code

Syntology Ran 0 of 6 code samples harvested from 1 repository linked to this paper; 6 have no recorded run.

By repository: official repository: 6 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

facebookresearch/hiera officialmentioned in paperpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested; 0 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

6unverified

Licence: 0 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from facebookresearch/hiera. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

apply_fusion_head facebookresearch/hiera/hiera/hiera_mae.py official repository unverified Apache-2.0 (permissive) · 815d1d88e2fbc27f · report
benchmark facebookresearch/hiera/hiera/benchmarking.py official repository unverified Apache-2.0 (permissive) · b160eae20550159c · report
conv_nd facebookresearch/hiera/hiera/hiera_utils.py official repository unverified Apache-2.0 (permissive) · 8a833cf7d1d043a1 · report
do_pool facebookresearch/hiera/hiera/hiera_utils.py official repository unverified Apache-2.0 (permissive) · 8b6a5042461e32ae · report
has_config facebookresearch/hiera/hiera/hfhub.py official repository unverified Apache-2.0 (permissive) · 5a74f72c4653f308 · report
pretrained_model facebookresearch/hiera/hiera/hiera_utils.py official repository unverified Apache-2.0 (permissive) · 85ff40001ae9f4c3 · report

Tasks

Action ClassificationAction RecognitionAction Recognition In VideosImage ClassificationInstance SegmentationObject DetectionVideo Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 Hiera-H (no extra data) Acc@1 87.8 #31 of 207 Archive leaderboard report
Action Classification Kinetics-600 Hiera-H (no extra data) Top-1 Accuracy 88.8 #18 of 65 Archive leaderboard report
Action Classification Kinetics-700 Hiera-H (no extra data) Top-1 Accuracy 81.1 #11 of 36 Archive leaderboard report
Action Recognition AVA v2.2 Hiera-H (K700 PT+FT) mAP 43.3 #2 of 38 Archive leaderboard report
Action Recognition Something-Something V2 Hiera-L (no extra data) Top-1 Accuracy 76.5 #7 of 123 Archive leaderboard report
Image Classification ImageNet Hiera-H Top 1 Accuracy 86.9% #115 of 1060 Archive leaderboard report
Image Classification Places365-Standard Hiera-H (448px) Top 1 Accuracy 60.6 #2 of 4 Archive leaderboard report
Image Classification iNaturalist Hiera-H (448px) Top 1 Accuracy 83.8 #2 of 19 Archive leaderboard report
Image Classification iNaturalist 2018 Hiera-H (448px) Top-1 Accuracy 87.3% #6 of 60 Archive leaderboard report
Image Classification iNaturalist 2019 Hiera-H (448px) Top-1 Accuracy 88.5 #1 of 22 Archive leaderboard report
Instance Segmentation COCO minival Heira-L mask AP 48.6 #34 of 93 Archive leaderboard report
Object Detection COCO minival Hiera-L box AP 55 #52 of 220 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections