Papers › Masked Feature Prediction for Self-Supervised Visual Pre-Training

Masked Feature Prediction for Self-Supervised Visual Pre-Training

16 Dec 2021CVPR 2022 1arXiv:2112.09133archive 2025-07-28

Chen Wei, Haoqi Fan, Saining Xie, Chao-yuan Wu, Alan Yuille, Christoph Feichtenhofer

We present Masked Feature Prediction (MaskFeat) for self-supervised pre-training of video models. Our approach first randomly masks out a portion of the input sequence and then predicts the feature of the masked regions. We study five different types of features and find Histograms of Oriented Gradients (HOG), a hand-crafted feature descriptor, works particularly well in terms of both performance and efficiency. We observe that the local contrast normalization in HOG is essential for good results, which is in line with earlier work using HOG for visual recognition. Our approach can learn abundant visual knowledge and drive large-scale Transformer-based models. Without using extra model weights or supervision, MaskFeat pre-trained on unlabeled videos achieves unprecedented results of 86.7% with MViT-L on Kinetics-400, 88.3% on Kinetics-600, 80.4% on Kinetics-700, 39.8 mAP on AVA, and 75.0% on SSv2. MaskFeat further generalizes to image input, which can be interpreted as a video with a single frame and obtains competitive results on ImageNet.

PaperPDFConference PDFCode

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

facebookresearch/SlowFast officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Reversible Vision Transformers (arXiv:2302.04869; that paper's own run record: 24 ran (of which 5 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
Westlake-AI/openmixup mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified), Visualizing the Loss Landscape of Neural Nets (arXiv:1712.09913; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified), CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (arXiv:1905.04899; that paper's own run record: 17 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
mx-mark/dmjd mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ConvMAE: Masked Convolution Meets Masked Autoencoders (arXiv:2205.03892; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
mx-mark/videotransformer-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Masked Autoencoders Are Scalable Vision Learners (arXiv:2111.06377; that paper's own run record: 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
yyk-wew/semanticmim mentioned on GitHubpytorchSyntology: not harvested report
open-mmlab/mmselfsup pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling (arXiv:2303.02416; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Action ClassificationAction RecognitionPredictionSelf-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 MaskFeat (K600, MViT-L) Acc@1 87.0 #42 of 207 Archive leaderboard report
Action Classification Kinetics-400 MaskFeat (K600, MViT-L) Acc@5 97.4 #42 of 207 Archive leaderboard report
Action Classification Kinetics-400 MaskFeat (no extra data, MViT-L) Acc@1 86.7 #45 of 207 Archive leaderboard report
Action Classification Kinetics-400 MaskFeat (no extra data, MViT-L) Acc@5 97.3 #45 of 207 Archive leaderboard report
Action Classification Kinetics-600 MaskFeat (no extra data, MViT-L) Top-1 Accuracy 88.3 #20 of 65 Archive leaderboard report
Action Classification Kinetics-600 MaskFeat (no extra data, MViT-L) Top-5 Accuracy 98.0 #20 of 65 Archive leaderboard report
Action Classification Kinetics-700 MaskFeat (no extra data, MViT-L) Top-1 Accuracy 80.4 #12 of 36 Archive leaderboard report
Action Classification Kinetics-700 MaskFeat (no extra data, MViT-L) Top-5 Accuracy 95.7 #12 of 36 Archive leaderboard report
Action Recognition AVA v2.2 MaskFeat (Kinetics-600 pretrain, MViT-L) mAP 39.8 #8 of 38 Archive leaderboard report
Action Recognition Something-Something V2 MaskFeat (Kinetics600 pretrain, MViT-L) GFLOPs 2828*3 #11 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MaskFeat (Kinetics600 pretrain, MViT-L) Parameters 218 #11 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MaskFeat (Kinetics600 pretrain, MViT-L) Top-1 Accuracy 75.0 #11 of 123 Archive leaderboard report
Action Recognition Something-Something V2 MaskFeat (Kinetics600 pretrain, MViT-L) Top-5 Accuracy 95.0 #11 of 123 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) MaskFeat (ViT-L) Number of Params 307M #21 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) MaskFeat (ViT-L) Top 1 Accuracy 85.7% #21 of 65 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

Local Contrast Normalization

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