A Multigrid Method for Efficiently Training Video Models

Conference on Computer Vision and Pattern Recognition (CVPR)


Training competitive deep video models is an order of magnitude slower than training their counterpart image models. Slow training causes long research cycles, which hinders progress in video understanding research. Following standard practice for training image models, video model training has used a fixed mini-batch shape: a specific number of clips, frames, and spatial size. However, what is the optimal shape? High resolution models perform well, but train slowly. Low resolution models train faster, but are less accurate. Inspired by multigrid methods in numerical optimization, we propose to use variable mini-batch shapes with different spatial-temporal resolutions that are varied according to a schedule. The different shapes arise from resampling the training data on multiple sampling grids. Training is accelerated by scaling up the mini-batch size and learning rate when shrinking the other dimensions. We empirically demonstrate a general and robust grid schedule that yields a significant out-of-the-box training speedup without a loss in accuracy for different models (I3D, nonlocal, SlowFast), datasets (Kinetics, Something-Something, Charades), and training settings (with and without pretraining, 128 GPUs or 1 GPU). As an illustrative example, the proposed multigrid method trains a ResNet-50 SlowFast network 4.5× faster (wall-clock time, same hardware) while also improving accuracy (+0.8% absolute) on Kinetics-400 compared to baseline training. Code is available online.

Related Publications

All Publications

Towards Generalization Across Depth for Monocular 3D Object Detection

Andrea Simonelli, Samuel Rota Bulò, Lorenzo Porzi, Elisa Ricci, Peter Kontschieder

ECCV - August 22, 2020

The Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scale

Christian Ertler, Jerneja Mislej, Tobias Ollmann, Lorenzo Porzi, Gerhard Neuhold, Yubin Kuang

ECCV - August 23, 2020

TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video

Tiancheng Zhi, Christoph Lassner, Tony Tung, Carsten Stoll, Srinivasa G. Narasimhan, Minh Vo

ECCV - August 21, 2020

Spatially Aware Multimodal Transformers for TextVQA

Yash Kant, Dhruv Batra, Peter Anderson, Alexander Schwing, Devi Parikh, Jiasen Lu, Harsh Agrawal

ECCV - August 23, 2020

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy