AI Paper Atlas

Research map / Detection and segmentation / CNN features

Multi-Stage Multi-Recursive-Input Fully Convolutional Networks for Neuronal Boundary Detection

Wei Shen, Bin Wang, Yuan Jiang, Yan Wang, Alan Yuille

ICCV 2017 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 62 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 a second stage (2-stage vs 1-stage) (ablation)M2FCN · Mouse piriform cortexRand F-score: 0.9688 -> 0.9819Improved
add a third stage (3-stage vs 2-stage) (ablation)M2FCN · Mouse piriform cortexRand F-score: 0.9819 -> 0.9866Improved
train single stage network for more iterations (ablation)single stage network · Mouse piriform cortexRand F-score: 0.9680 -> 0.9688No clear effect
use multiple recursive inputs instead of only level-5 side output (ablation)2-stage M2FCN · Mouse piriform cortexRand F-score: 0.9410 -> 0.9819Improved
use multiple recursive inputs instead of only level-4 side output (ablation)2-stage M2FCN · Mouse piriform cortexRand F-score: 0.9656 -> 0.9819Improved
train stages end-to-end instead of stepwise (ablation)2-stage M2FCN · Mouse piriform cortexRand F-score: 0.9762 -> 0.9819Improved
add fifth level to each sub-net (wide receptive field range) (ablation)2-stage M2FCN · Mouse piriform cortexRand F-score: 0.9739 -> 0.9819Improved
use end-to-end 2-stage 2D M2FCN instead of VD2D3D (ablation)M2FCN · Mouse piriform cortexRand F-score: 0.9720 -> 0.9819Improved
use M2FCN (2-stage) instead of CUMedVisionM2FCN · ISBI 2012 EM testRand F-score: 0.9768 -> 0.9780Improved
use M2FCN (2-stage) instead of PolyMtlM2FCN · ISBI 2012 EM testRand F-score: 0.9806 -> 0.9780Hurt

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