Performer

2 Posts

Architecture of CXV
Performer

Upgrade for Vision Transformers: Improved Efficiency for Vision Transformers

Vision Transformer and models like it use a lot of computation and memory when processing images. New work modifies these architectures to run more efficiently while adopting helpful properties from convolutions.
Graph showing information about different transformer models
Performer

Transformer Variants Head to Head

The transformer architecture has inspired a plethora of variations. Yet researchers have used a patchwork of metrics to evaluate their performance, making them hard to compare. New work aims to level the playing field.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox