Papers › Masked Event Modeling: Self-Supervised Pretraining for Event Cameras

Masked Event Modeling: Self-Supervised Pretraining for Event Cameras

20 Dec 2022arXiv:2212.10368archive 2025-07-28

Simon Klenk, David Bonello, Lukas Koestler, Nikita Araslanov, Daniel Cremers

Event cameras asynchronously capture brightness changes with low latency, high temporal resolution, and high dynamic range. However, annotation of event data is a costly and laborious process, which limits the use of deep learning methods for classification and other semantic tasks with the event modality. To reduce the dependency on labeled event data, we introduce Masked Event Modeling (MEM), a self-supervised framework for events. Our method pretrains a neural network on unlabeled events, which can originate from any event camera recording. Subsequently, the pretrained model is finetuned on a downstream task, leading to a consistent improvement of the task accuracy. For example, our method reaches state-of-the-art classification accuracy across three datasets, N-ImageNet, N-Cars, and N-Caltech101, increasing the top-1 accuracy of previous work by significant margins. When tested on real-world event data, MEM is even superior to supervised RGB-based pretraining. The models pretrained with MEM are also label-efficient and generalize well to the dense task of semantic image segmentation.

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="2212.10368")

Code

Syntology Ran 5 of 18 code samples harvested from 1 repository linked to this paper; 13 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · violated contract; 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 18 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

tum-vision/mem officialmentioned in papermentioned on GitHubpytorchApache-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

18 samples harvested; 5 ran; 1 honoured the contract we drafted; 13 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.

1ran · honoured contract
2ran · violated contract
1ran · our draft was wrong
1ran
13unverified

Licence: 0 of the 18 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 tum-vision/mem. “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.

default tum-vision/mem/mem/modeling_discrete_vae.py official repository ran · violated contract fingerprinted Apache-2.0 (permissive) · 60fff7c3c400d7ff · report
exists tum-vision/mem/mem/modeling_discrete_vae.py official repository ran · violated contract Apache-2.0 (permissive) · aa5486a3650902d8 · report
get_num_layer_for_vit tum-vision/mem/mem/optim_factory.py official repository ran fingerprinted Apache-2.0 (permissive) · a3448702d6025ce6 · report
pil_loader tum-vision/mem/mem/dataset_folder.py official repository ran · honoured contract Apache-2.0 (permissive) · f6be833ba409926f · report
top_k tum-vision/mem/mem/modeling_discrete_vae.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · fc2efb619b6ee2c4 · report
accimage_loader tum-vision/mem/mem/dataset_folder.py official repository unverified Apache-2.0 (permissive) · e668ee56928fd57d · report
get_1d_sincos_pos_embed_from_grid tum-vision/mem/mem/modeling_mae.py official repository unverified Apache-2.0 (permissive) · 12035a2f77d8016c · report
get_2d_sincos_pos_embed tum-vision/mem/mem/modeling_mae.py official repository unverified Apache-2.0 (permissive) · 3185afc3e87293ed · report
get_2d_sincos_pos_embed_from_grid tum-vision/mem/mem/modeling_mae.py official repository unverified Apache-2.0 (permissive) · f10004e059714d42 · report
get_loss_scale_for_deepspeed tum-vision/mem/mem/engine_for_finetuning.py official repository unverified Apache-2.0 (permissive) · 29416043c7035e7c · report
get_model tum-vision/mem/mem/run_mem_pretraining.py official repository unverified Apache-2.0 (permissive) · 5d9ee4d7cd9eacc7 · report
get_parameter_groups tum-vision/mem/mem/optim_factory.py official repository unverified Apache-2.0 (permissive) · 0ef0019514eaaa09 · report
get_valid_flow tum-vision/mem/mem/dataset_folder.py official repository unverified Apache-2.0 (permissive) · 690ba46b598729b5 · report
is_valid_file_dsec tum-vision/mem/mem/datasets.py official repository unverified Apache-2.0 (permissive) · 6dd91e35fd03983c · report
is_valid_file_mvsec tum-vision/mem/mem/datasets.py official repository unverified Apache-2.0 (permissive) · 40dede0d13c8dfae · report
plot_mae tum-vision/mem/mem/engine_for_pretraining.py official repository unverified Apache-2.0 (permissive) · 96e4c97a4c23a9d1 · report
plot_masks_and_images tum-vision/mem/mem/engine_for_pretraining.py official repository unverified Apache-2.0 (permissive) · bfe177b133a4d710 · report
train_class_batch tum-vision/mem/mem/engine_for_finetuning.py official repository unverified Apache-2.0 (permissive) · c7976ea27edc377a · report

Tasks

ClassificationEvent-based visionImage SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Classification N-CARS MEM Accuracy (%) 98.55 #1 of 6 Archive leaderboard report
Classification N-CARS MEM Architecture Transformer #1 of 6 Archive leaderboard report
Classification N-CARS MEM Representation Event Histogram #1 of 6 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