Papers › MultiMAE: Multi-modal Multi-task Masked Autoencoders

MultiMAE: Multi-modal Multi-task Masked Autoencoders

4 Apr 2022arXiv:2204.01678archive 2025-07-28

Roman Bachmann, David Mizrahi, Andrei Atanov, Amir Zamir

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input besides the RGB image (hence "multi-modal"), and II) its training objective accordingly includes predicting multiple outputs besides the RGB image (hence "multi-task"). We make use of masking (across image patches and input modalities) to make training MultiMAE tractable as well as to ensure cross-modality predictive coding is indeed learned by the network. We show this pre-training strategy leads to a flexible, simple, and efficient framework with improved transfer results to downstream tasks. In particular, the same exact pre-trained network can be flexibly used when additional information besides RGB images is available or when no information other than RGB is available - in all configurations yielding competitive to or significantly better results than the baselines. To avoid needing training datasets with multiple modalities and tasks, we train MultiMAE entirely using pseudo labeling, which makes the framework widely applicable to any RGB dataset. The experiments are performed on multiple transfer tasks (image classification, semantic segmentation, depth estimation) and datasets (ImageNet, ADE20K, Taskonomy, Hypersim, NYUv2). The results show an intriguingly impressive capability by the model in cross-modal/task predictive coding and transfer.

PaperPDFCodeMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

EPFL-VILAB/MultiMAE officialmentioned on GitHubpytorchNOASSERTIONSyntology: not harvested 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for MultiMAE (graph method: MultiMAE). 8 bricks; individually on a fixture: 7 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. MultiMAE entry · level 0 · unverified · ab3aedef666eb507
  2. Block helper · level 1 · ran · 3cb7e68ce1e3f5f2
  3. trunc_normal_ helper · level 1 · ran; the contract check could not run · 605878f6dcef72e9
  4. Attention helper · level 1 · ran · d969a5ba04920f2e
  5. DropPath helper · level 1 · ran · e6e9f6bf7f63ce5e
  6. Mlp helper · level 1 · ran · 1bd4afb036e3fc07
  7. drop_path helper · level 1 · ran; the contract check could not run · 3ac6b7d76e8e3584
  8. _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run · 813ed3a96c17cf42

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2204.01678") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Depth EstimationImage ClassificationSemantic Segmentationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation ADE20K MultiMAE (ViT-B) Validation mIoU 46.2 #180 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val MultiMAE (ViT-B) mIoU 46.2 #73 of 95 Archive leaderboard report
Semantic Segmentation Hypersim MultiMAE (ViT-B) mIoU 37.0 #2 of 5 Archive leaderboard report
Semantic Segmentation Hypersim MAE (ViT-B) mIoU 36.5 #3 of 5 Archive leaderboard report
Semantic Segmentation Hypersim DINO (ViT-B) mIoU 32.5 #4 of 5 Archive leaderboard report
Semantic Segmentation Hypersim MoCo-v3 (ViT-B) mIoU 31.7 #5 of 5 Archive leaderboard report
Semantic Segmentation NYU Depth v2 MultiMAE (ViT-B) Mean IoU 56.0% #22 of 121 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.

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