most citedDepth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks

8 citations · 9 across the 2 of their papers we have counts for

collaborators
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2024★ 1 cited

Segment Anything Model for Road Network Graph Extraction

Congrui Hetang, Haoru Xue, Cindy Le +3

We propose SAM-Road, an adaptation of the Segment Anything Model (SAM) for extracting large-scale, vectorized road network graphs from satellite imagery. To predict graph geometry,…

cs.CV2019★ 8 cited

Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks

Yihui He, Jianing Qian, Jianren Wang +5

Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, wh…