AI Paper Atlas

Research map / Detection and segmentation / CNN features

Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network

Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun

CVPR 2017 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 1,737 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Increase GCN kernel size from 3 to 15 (ablation)GCN segmentation model · PASCAL VOC 2012 valmean IoU: 70.1 -> 74.5Improved
Replace GCN with a trivial k×k convolution (ablation)GCN segmentation model · PASCAL VOC 2012 valmean IoU: 70.1 -> 69.8; 71.1 -> 70.4; 72.8 -> 69.6; 73.4 -> 68.8Hurt
Replace GCN with a stack of small convolutions (ablation)GCN segmentation model · PASCAL VOC 2012 val, large equivalent kernelsmean IoU: GCN/Stack: 70.1/69.8, 71.1/71.8, 72.8/71.3, 73.4/69.5, 73.7/67.5Mixed
Reduce intermediate channels in a convolution stack (ablation)Stack of small convolutions, compared with GCN · PASCAL VOC 2012 valmean IoU: 71.3 -> 70.4 -> 68.8; GCN: 72.8Hurt
Add boundary refinement to GCN (ablation)GCN segmentation model · PASCAL VOC 2012 val, boundary pixelsaccuracy: 71.5 -> 73.4Improved
Add GCN with k=15 (ablation)1×1 convolution baseline · PASCAL VOC 2012 val, internal pixelsaccuracy: 93.9 -> 95.0Improved
Add boundary refinement to GCN (ablation)GCN segmentation model · PASCAL VOC 2012 val, internal pixelsaccuracy: 95.0 -> 95.1No clear effect
Replace the first two ResNet bottleneck layers with GCN (ablation)ResNet50 segmentation model · PASCAL VOC 2012 valmean IoU: 65.7 -> 71.2Improved
Use ResNet50-GCN instead of ResNet50 as the pretrained model, with GCN + BR (ablation)GCN + BR segmentation model · PASCAL VOC 2012 valmean IoU: 72.3 -> 72.5No clear effect
Add boundary refinement to GCN (ablation)PASCAL VOC 2012 Stage-3 model · PASCAL VOC 2012 valmean IoU: 78.7 -> 80.3Improved
Apply multi-scale evaluation (ablation)PASCAL VOC 2012 Stage-3 GCN + BR · PASCAL VOC 2012 valmean IoU: 80.3 -> 80.4No clear effect
Apply denseCRF post-processing after multi-scale evaluation (ablation)PASCAL VOC 2012 Stage-3 GCN + BR · PASCAL VOC 2012 valmean IoU: 80.4 -> 81.0Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy