AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Fast Image Processing With Fully-Convolutional Networks

Qifeng Chen, Jia Xu, Vladlen Koltun

ICCV 2017 · Architectures and efficiency › CNN design · approach: Efficient CNN scaling and dynamic inference · 363 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 adaptive normalization instead of no normalization (ablation)CAN32 · MIT-Adobe 5K test (avg over 10 operators)PSNR: 35.52 -> 37.59Improved
use adaptive normalization instead of plain batch normalization (ablation)CAN32 · MIT-Adobe 5K test (avg over 10 operators)PSNR: 28.64 -> 37.59Improved
add batch normalization alone (no identity branch) (ablation)CAN32 · MIT-Adobe 5K test (avg over 10 operators)PSNR: 35.52 -> 28.64Hurt
increase depth and width (d=9,w=24 to d=10,w=32), receptive field 257 to 513 (ablation)CAN+AN · MIT-Adobe 5K test (avg over 10 operators)PSNR: 36.04 -> 37.59Improved
increase depth and width (d=9,w=24 to d=10,w=32) (ablation)CAN+AN · MIT-Adobe 5K test (avg over 10 operators)runtime (ms): 190 -> 277Hurt
train separate networks per operator instead of one shared network (ablation)CAN32+AN · MIT-Adobe 5K test (avg over 10 operators)PSNR: 29.86 -> 37.59Improved
use CAN32 instead of Plain network (ablation)fully-convolutional · MIT-Adobe 5K test (avg over 10 operators)PSNR: 32.05 -> 35.52Improved
use dilated context aggregation CAN32+AN instead of encoder-decoderfully-convolutional · MIT-Adobe 5K test (avg over 10 operators)PSNR: 34.90 -> 37.59Improved
use CAN24+AN instead of FCN-8sfully-convolutional · MIT-Adobe 5K test (avg over 10 operators)PSNR: 26.36 -> 36.04Improved
use perceptual or adversarial loss instead of MSE (ablation)CAN · MIT-Adobe 5K test (avg over 10 operators)approximation accuracyNo clear effect
use CAN approximator instead of BGU-optimage operators · MIT-Adobe 5K test (avg over 10 operators)PSNR: 25 -> 36Improved

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