EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
- URL: http://arxiv.org/abs/2211.10636v6
- Date: Thu, 20 Jun 2024 03:41:16 GMT
- Title: EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
- Authors: Sunil Hwang, Jaehong Yoon, Youngwan Lee, Sung Ju Hwang,
- Abstract summary: We present EVEREST, a surprisingly efficient MVA approach for video representation learning.
It finds tokens containing rich motion features and discards uninformative ones during both pre-training and fine-tuning.
Our method significantly reduces the computation and memory requirements of MVA.
- Score: 57.354304637367555
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Masked Video Autoencoder (MVA) approaches have demonstrated their potential by significantly outperforming previous video representation learning methods. However, they waste an excessive amount of computations and memory in predicting uninformative tokens/frames due to random masking strategies. (e.g., over 16 nodes with 128 NVIDIA A100 GPUs). To resolve this issue, we exploit the unequal information density among the patches in videos and propose EVEREST, a surprisingly efficient MVA approach for video representation learning that finds tokens containing rich motion features and discards uninformative ones during both pre-training and fine-tuning. We further present an information-intensive frame selection strategy that allows the model to focus on informative and causal frames with minimal redundancy. Our method significantly reduces the computation and memory requirements of MVA, enabling the pre-training and fine-tuning on a single machine with 8 GPUs while achieving comparable performance to computation- and memory-heavy baselines on multiple benchmarks and the uncurated Ego4D dataset. We hope that our work contributes to reducing the barrier to further research on video understanding.
Related papers
- Extending Video Masked Autoencoders to 128 frames [75.01251612160829]
Video understanding has witnessed significant progress with recent video foundation models demonstrating strong performance owing to self-supervised pre-training objectives; Masked Autoencoders (MAE) being the design of choice.
However, the majority of prior works that leverage MAE pre-training have focused on relatively short video representations (16 / 32 frames in length) largely due to hardware memory and compute limitations that scale poorly with video length due to the dense memory-intensive self-attention decoding.
We propose an effective strategy for prioritizing tokens which allows training on longer video sequences (128 frames) and gets better performance than, more typical, random
arXiv Detail & Related papers (2024-11-20T20:00:38Z) - VideoLLaMB: Long-context Video Understanding with Recurrent Memory Bridges [42.555895949250704]
VideoLLaMB is a novel framework that utilizes temporal memory tokens within bridge layers to allow for the encoding of entire video sequences.
SceneTilling algorithm segments videos into independent semantic units to preserve semantic integrity.
In terms of efficiency, VideoLLaMB, trained on 16 frames, supports up to 320 frames on a single Nvidia A100 GPU.
arXiv Detail & Related papers (2024-09-02T08:52:58Z) - VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation [66.00245701441547]
We introduce a novel approach to reduce vision compute by leveraging redundant vision tokens "skipping layers" rather than decreasing the number of vision tokens.
Our method, VideoLLM-MoD, is inspired by mixture-of-depths LLMs and addresses the challenge of numerous vision tokens in long-term or streaming video.
arXiv Detail & Related papers (2024-08-29T17:21:58Z) - A Simple Recipe for Contrastively Pre-training Video-First Encoders
Beyond 16 Frames [54.90226700939778]
We build on the common paradigm of transferring large-scale, image--text models to video via shallow temporal fusion.
We expose two limitations to the approach: (1) decreased spatial capabilities, likely due to poor video--language alignment in standard video datasets, and (2) higher memory consumption, bottlenecking the number of frames that can be processed.
arXiv Detail & Related papers (2023-12-12T16:10:19Z) - VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking [57.552798046137646]
Video masked autoencoder (VideoMAE) is a scalable and general self-supervised pre-trainer for building video foundation models.
We successfully train a video ViT model with a billion parameters, which achieves a new state-of-the-art performance.
arXiv Detail & Related papers (2023-03-29T14:28:41Z) - Masked Autoencoders As Spatiotemporal Learners [60.83955416682043]
This paper studies a conceptually simple extension of Masked Autoencoders (MAE) totemporal representation learning from videos.
We randomly mask out spacetime patches in videos and learn an autoencoder to reconstruct them in pixels.
We observe that the optimal masking ratio is as high as 90% (vs. 75% on images), supporting the hypothesis that this ratio is related to information redundancy of the data.
arXiv Detail & Related papers (2022-05-18T17:59:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.