Unmasked Teacher: Towards Training-Efficient Video Foundation Models
Authors:
Preprint
Abstract
Video Foundation Models (VFMs) have received limited exploration due to high computational costs and data scarcity. Previous VFMs rely on Image Foundation Models (IFMs), which face challenges in transferring to the video domain. Although VideoMAE has trained a robust ViT from limited data, its low-level reconstruction poses convergence difficulties and conflicts with high-level cross-modal alignment. This paper proposes a training-efficient method for temporal-sensitive VFMs that integrates the benefits of existing methods. To increase data efficiency, we mask out most of the low-semantics video tokens, but selectively align the unmasked tokens with IFM, which serves as the UnMasked Teacher (UMT). By providing semantic guidance, our method enables faster convergence and multimodal friendliness. With a progressive pre-training framework, our model can handle various tasks including scene-related, temporal-related, and complex video-language understanding. Using only public sources for pre-training in 6 days on 32 A100 GPUs, our scratch-built ViT-L/16 achieves state-of-the-art performances on various video tasks. The code and models will be released at https://github.com/OpenGVLab/unmasked_teacher.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Context Autoencoder for Self-supervised Representation LearningInternational Journal of Computer Vision, 2023
- Siamese Image Modeling for Self-Supervised Vision Representation Learning2023
- MVP: Multimodality-Guided Visual Pre-training2022
- Expanding Language-Image Pretrained Models for General Video Recognition2022
- CLIP4Clip: An empirical study of CLIP for end to end video clip retrieval and captioningNeurocomputing, 2022
- MViTv2: Improved Multiscale Vision Transformers for Classification and Detection2022
- Semantic Understanding of Scenes Through the ADE20K DatasetInternational Journal of Computer Vision, 2018
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image AnnotationsInternational Journal of Computer Vision, 2017
- Deep Networks with Stochastic Depth2016
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition2016