AI Paper Atlas

Research map / Detection and segmentation / CNN features

Scale-Adaptive Convolutions for Scene Parsing

Rui Zhang, Sheng Tang, Yongdong Zhang, Jintao Li, Shuicheng Yan

ICCV 2017 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 184 citations (OpenAlex)

Read the paperCheck 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
add scale-adaptive convolution in last layer, jointly trained (ablation)Baseline ResNet-101 · Cityscapes valmean IoU: 74.0 -> 75.9Improved
add scale-adaptive convolutions in last layer and 5th block 3x3 layers (ablation)Baseline ResNet-101 · Cityscapes valmean IoU: 74.0 -> 76.5Improved
learn only scale regression layer with other weights fixed (single) (ablation)Baseline ResNet-101 · Cityscapes valmean IoU: 74.0 -> 74.5Improved
learn only scale regression layers with weights fixed (multiple) (ablation)Baseline ResNet-101 · Cityscapes valmean IoU: 74.0 -> 74.8Improved
jointly train convolution parameters with scale coefficients instead of fixing them (ablation)SAC-single · Cityscapes valmean IoU: 74.5 -> 75.9Improved
use multiple scale-adaptive layers instead of single (ablation)SAC · Cityscapes valmean IoU: 75.9 -> 76.5Improved
add multi-scale fusion at test time (ablation)SAC-multiple · Cityscapes valmean IoU: 76.5 -> 78.7Improved
add scale-adaptive convolution in last layer, jointly trained (ablation)Baseline ResNet-101 · ADE20K valmean IoU: 39.75 -> 41.68Improved
add multiple scale-adaptive layers (ablation)Baseline ResNet-101 · ADE20K valmean IoU: 39.75 -> 42.38Improved
fixed weights, only scale regression trained (single) (ablation)Baseline ResNet-101 · ADE20K valmean IoU: 39.75 -> 40.32Improved
fixed weights, only scale regression trained (multiple) (ablation)Baseline ResNet-101 · ADE20K valmean IoU: 39.75 -> 40.87Improved
add multi-scale fusion at test time (ablation)SAC-multiple · ADE20K valmean IoU: 42.38 -> 44.30Improved

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