Picture for Thomas Verelst

Thomas Verelst

Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations

Add code
Mar 11, 2022
Figure 1 for Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations
Figure 2 for Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations
Figure 3 for Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations
Figure 4 for Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations
Viaarxiv icon

BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies

Add code
Aug 20, 2021
Figure 1 for BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies
Figure 2 for BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies
Figure 3 for BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies
Figure 4 for BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies
Viaarxiv icon

SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation

Add code
Nov 24, 2020
Figure 1 for SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation
Figure 2 for SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation
Figure 3 for SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation
Figure 4 for SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation
Viaarxiv icon

Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference

Add code
Dec 06, 2019
Figure 1 for Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference
Figure 2 for Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference
Figure 3 for Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference
Figure 4 for Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference
Viaarxiv icon

Generating superpixels using deep image representations

Add code
Mar 11, 2019
Figure 1 for Generating superpixels using deep image representations
Figure 2 for Generating superpixels using deep image representations
Figure 3 for Generating superpixels using deep image representations
Figure 4 for Generating superpixels using deep image representations
Viaarxiv icon