NVIDIA’s Global Context ViT Achieves SOTA Performance on CV Tasks Without Expensive Computation

In the new paper Global Context Vision Transformers, an NVIDIA research team proposes the Global Context Vision Transformer, a novel yet simple hierarchical ViT architecture comprising global self-attention and token generation modules that enables the efficient modelling of both short- and long-range dependencies without costly compute operations while achieving SOTA results across various computer vision tasks.

ai artificial intelligence computation computer vision & graphics context cv deep-neural-networks global machine learning machine learning & data science ml nvidia performance research sota technology transformer vision-transformer