A Multigrid Method for Efficiently Training Video Models

Understand

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 assumes 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.