175 citations · 213 across the 5 of their papers we have counts for
5 papers · 1 filter
Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations
Thomas Verelst, Paul K. Rubenstein, Marcin Eichner +2
As natural images usually contain multiple objects, multi-label image classification is more applicable "in the wild" than single-label classification. However, exhaustively annota…
BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies
Thomas Verelst, Tinne Tuytelaars
In this paper we propose BlockCopy, a scheme that accelerates pretrained frame-based CNNs to process video more efficiently, compared to standard frame-by-frame processing. To this…
SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation
Thomas Verelst, Tinne Tuytelaars
SegBlocks reduces the computational cost of existing neural networks, by dynamically adjusting the processing resolution of image regions based on their complexity. Our method spli…
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…
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…