Papers › Masked Feature Prediction for Self-Supervised Visual Pre-Training
Masked Feature Prediction for Self-Supervised Visual Pre-Training
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.
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):
get_citation_path(paper_1="2112.09133", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2112.09133")
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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