Search Results for author:
Found 3 papers, 1 papers with code
EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction
Without performance loss on Cityscapes, our EfficientViT provides up to 8. 8x and 3. 8x GPU latency reduction over SegFormer and SegNeXt, respectively.
OLLIE: Derivation-based Tensor Program Optimizer
Boosting the runtime performance of deep neural networks (DNNs) is critical due to their wide adoption in real-world tasks.
EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction
Without performance loss on Cityscapes, our EfficientViT provides up to 13. 9$\times$ and 6. 2$\times$ GPU latency reduction over SegFormer and SegNeXt, respectively.
Ranked #23 on
Semantic Segmentation
on Cityscapes val
