Papers › AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders

AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders

16 Nov 2022CVPR 2023 1arXiv:2211.09120archive 2025-07-28

Wele Gedara Chaminda Bandara, Naman Patel, Ali Gholami, Mehdi Nikkhah, Motilal Agrawal, Vishal M. Patel

Masked Autoencoders (MAEs) learn generalizable representations for image, text, audio, video, etc., by reconstructing masked input data from tokens of the visible data. Current MAE approaches for videos rely on random patch, tube, or frame-based masking strategies to select these tokens. This paper proposes AdaMAE, an adaptive masking strategy for MAEs that is end-to-end trainable. Our adaptive masking strategy samples visible tokens based on the semantic context using an auxiliary sampling network. This network estimates a categorical distribution over spacetime-patch tokens. The tokens that increase the expected reconstruction error are rewarded and selected as visible tokens, motivated by the policy gradient algorithm in reinforcement learning. We show that AdaMAE samples more tokens from the high spatiotemporal information regions, thereby allowing us to mask 95% of tokens, resulting in lower memory requirements and faster pre-training. We conduct ablation studies on the Something-Something v2 (SSv2) dataset to demonstrate the efficacy of our adaptive sampling approach and report state-of-the-art results of 70.0% and 81.7% in top-1 accuracy on SSv2 and Kinetics-400 action classification datasets with a ViT-Base backbone and 800 pre-training epochs.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 25 code samples harvested from 2 repositories linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 14 ran (10 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 10 samples from 1 repository, 4 ran (3 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

wgcban/adamae officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 14 ran (4 instrument-failed) · 1 unverified report
Nithin-GK/UniteandConquer mentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 4 ran (1 instrument-failed) · 6 unverified 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

25 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
5ran · our draft was wrong
12ran
7unverified

Licence: 6 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

wgcban/adamae official repository 15 samples, 14 ran (4 instrument-failed) · 1 unverified
CE_loss in 5 papers msc/losses.py ran MIT (permissive) · 0d86b6995e23b2d4 · report fixture: signature input_logits:Tensor/2/float, target_targets:Tensor/1/int, temperature:float/0/float · returned Tensor · level recorded 2026-09-25
crop_clip in 14 papers functional.py ran MIT (permissive) · bc39b8ed5fefa7eb · report fixture: signature clip:list/1/ndarray, min_h:int/0/int, min_w:int/0/int, h:int/0/int, w:int/0/int · returned list · level recorded 2026-09-24
get_alpha in 12 papers msc/losses.py ran MIT (permissive) · 612575eeaa3ae40c · report fixture: signature supervised_loader:list/1/tuple · returned list · level recorded 2026-09-25
get_loss_scale_for_deepspeed in 20 papers msc/engine_for_finetuning.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 29416043c7035e7c · report fixture: signature model:callable/0/? · returned float · level recorded 2026-09-25
get_num_layer_for_vit in 23 papers optim_factory.py ran fingerprinted MIT (permissive) · a3448702d6025ce6 · report fixture: signature var_name:str/0/str, num_max_layer:int/0/int · returned int · level recorded 2026-09-24
get_parameter_groups in 30 papers optim_factory.py ran MIT (permissive) here; the stored copy is pointer only · 0ef0019514eaaa09 · report fixture: signature model:callable/0/?, weight_decay:float/0/float, skip_list:tuple/1/empty, get_num_layer:callable/0/?, get_layer_scale:callable/0/? · returned list · level recorded 2026-09-25
get_resize_sizes in 11 papers functional.py ran MIT (permissive) · 2b53e457d5632b4e · report fixture: signature im_h:int/0/int, im_w:int/0/int, size:int/0/int · returned tuple · level recorded 2026-09-24
resize_clip in 14 papers functional.py ran MIT (permissive) · 981936c73d3cdd12 · report fixture: signature clip:list/1/ndarray, size:int/0/int, interpolation:str/0/str · returned list · level recorded 2026-09-24
shear_x in 43 papers rand_augment.py ran · our draft was wrong MIT (permissive) · e866e1196986f728 · report fixture: signature img:Image/0/?, factor:float/0/float, resample:int/0/int, fillcolor:tuple/1/int · returned Image · level recorded 2026-09-24
shear_y in 37 papers rand_augment.py ran · our draft was wrong MIT (permissive) · 7b2503c99c9447fb · report fixture: signature img:Image/0/?, factor:float/0/float, resample:int/0/int, fillcolor:tuple/1/int · returned Image · level recorded 2026-09-24
softmax_helper msc/losses.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · c66339fca70da624 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-26
tensor_normalize in 18 papers kinetics.py ran MIT (permissive) here; the stored copy is pointer only · 14b3b13b2e7ee844 · report fixture: signature tensor:Tensor/2/int, mean:list/1/float, std:list/1/float · returned Tensor · level recorded 2026-09-25
train_class_batch in 17 papers msc/engine_for_finetuning.py ran MIT (permissive) here; the stored copy is pointer only · c7976ea27edc377a · report fixture: signature model:callable/0/?, samples:Tensor/2/float, target:Tensor/1/int, criterion:callable/0/? · returned tuple · level recorded 2026-09-25
translate_x_rel in 27 papers rand_augment.py ran · our draft was wrong MIT (permissive) · 323759f906fbb394 · report fixture: signature img:Image/0/?, pct:float/0/float, resample:int/0/int, fillcolor:tuple/1/int · returned Image · level recorded 2026-09-24
get_model in 368 papers pretrain_mae_vit.py unverified MIT (permissive) · cd41abe0ddd75bc6 · report
Nithin-GK/UniteandConquer community (archive-listed) 10 samples, 4 ran (1 instrument-failed) · 6 unverified
args_to_dict in 8 papers class_utils/script_util.py ran Apache-2.0 (permissive) · 4e2ac192b520c457 · report fixture: signature args:Args/0/?, keys:list/1/str · returned dict · level recorded 2026-09-24
d_clip_loss face_utils/farl_text.py ran fingerprinted Apache-2.0 (permissive) · 65ce936001e1e5a2 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float, use_cosine:bool/0/bool · returned Tensor · level recorded 2026-09-25
greet gradio_set.py ran fingerprinted Apache-2.0 (permissive) · 95f14a0c91022fc2 · report fixture: signature name:str/0/str · returned str · level recorded 2026-09-25
zero_module in 184 papers class_utils/nn.py ran · our draft was wrong Apache-2.0 (permissive) · 129b804760b3115f · report fixture: signature module:callable/0/? · returned SimpleModule · level recorded 2026-09-22
avg_pool_nd in 83 papers class_utils/nn.py unverified Apache-2.0 (permissive) · ecd0fc28815b65ae · report
class_find gradio_set.py unverified Apache-2.0 (permissive) · d046b61348049e13 · report
conv_nd in 94 papers class_utils/nn.py unverified Apache-2.0 (permissive) · fe4eb545bbb728e0 · report
create_model in 163 papers class_utils/script_util.py unverified Apache-2.0 (permissive) · 2234d67e4ed38722 · report
fetch_file_cached in 6 papers utils/download_models_func.py unverified Apache-2.0 (permissive) · 3081b94d2db18290 · report
get_confirm_token in 41 papers utils/download_models_func.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 135b3dc835ffe6ad · report

Tasks

Action ClassificationRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 AdaMAE Acc@1 81.7 #81 of 207 Archive leaderboard report
Action Classification Kinetics-400 AdaMAE Acc@5 95.2 #81 of 207 Archive leaderboard report
Action Classification Something-Something V2 AdaMAE Acc@1 70.04 #1 of 1 Archive leaderboard report
Action Classification Something-Something V2 AdaMAE Acc@5 92.7 #1 of 1 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

Adaptive MaskingL1 RegularizationMAEMasked Convolution

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