X3D: Expanding Architectures for Efficient Video Recognition

Christoph Feichtenhofer
4/9/2020
cs.CV

Official code: facebookresearch/SlowFast (7,436 stars, Apache-2.0, last commit 2026-03-16).

Abstract

This paper presents X3D, a family of efficient video networks that progressively expand a tiny 2D image classification architecture along multiple network axes, in space, time, width and depth. Inspired by feature selection methods in machine learning, a simple stepwise network expansion approach is employed that expands a single axis in each step, such that good accuracy to complexity trade-off is achieved. To expand X3D to a specific target complexity, we perform progressive forward expansion followed by backward contraction. X3D achieves state-of-the-art performance while requiring 4.8x and 5.5x fewer multiply-adds and parameters for similar accuracy as previous work. Our most surprising finding is that networks with high spatiotemporal resolution can perform well, while being extremely light in terms of network width and parameters. We report competitive accuracy at unprecedented efficiency on video classification and detection benchmarks. Code will be available at: https://github.com/facebookresearch/SlowFast

View on arXivView PDF

Code Implementations(1)

facebookresearch/SlowFastOfficial100%
Apache-2.0

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

7,4361,296Shell, PythonAug 20, 20197 months agoApache-2.0

Similar Papers

CBinfer: Exploiting Frame-to-Frame Locality for Faster Convolutional Network Inference on Video Streams

84% match1 repo102018

MoViNets: Mobile Video Networks for Efficient Video Recognition

84% match1 repo77.7k2021

Differentiable Resolution Compression and Alignment for Efficient Video Classification and Retrieval

83% match1 repo62023

S3TC: Spiking Separated Spatial and Temporal Convolutions with Unsupervised STDP-based Learning for Action Recognition

83% match2023

Aggregated Residual Transformations for Deep Neural Networks

83% match1 repo1.9k2016

Fixed-Point Convolutional Neural Network for Real-Time Video Processing in FPGA

83% match1 repo3142018

Cite this paper

@article{feichtenhofer2020xd,
  title  = {X3D: Expanding Architectures for Efficient Video Recognition},
  author = {Christoph Feichtenhofer},
  year   = {2020},
  eprint = {2004.04730},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2004.04730}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2004.04730.svg)](https://codeofpaper.com/paper/2004.04730)

Discussion