175 citations · 213 across the 5 of their papers we have counts for
Showing 2019 · cs.CVShow all
2 papers · 2 filters
cs.CV2019★ 175 cited
Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference
Thomas Verelst, Tinne Tuytelaars
Modern convolutional neural networks apply the same operations on every pixel in an image. However, not all image regions are equally important. To address this inefficiency, we pr…
cs.CV2019★ 2 cited
Generating superpixels using deep image representations
Thomas Verelst, Matthew Blaschko, Maxim Berman
Superpixel algorithms are a common pre-processing step for computer vision algorithms such as segmentation, object tracking and localization. Many superpixel methods only rely on c…