Paper Info
Title
Masked Feature Prediction for Self-Supervised Visual Pre-Training
Abstract
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 pretrained on unlabeled videos achieves unprecedented results of 86.7% with MViTv2-L on Kinetics-400, 88.3% on Kinetics 600, 80.4% on Kinetics-700, 38.8 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 ImageN et.
Year
DOI
Venue
2022
10.1109/CVPR52688.2022.01426
IEEE Conference on Computer Vision and Pattern Recognition
Keywords
DocType
Volume
Self-& semi-& meta- Recognition: detection,categorization,retrieval, Video analysis and understanding
Conference
2022
Issue
Citations 
PageRank 
1
0
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Wei Chen101.69
Haoqi Fan21096.75
Saining Xie323112.45
Chao-Yuan Wu400.34
Alan L. Yuille5103391902.01
Christoph Feichtenhofer651920.44