AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching

Qiang Wang, Shaohuai Shi, Kaiyong Zhao, Xiaowen Chu

ECCV 2022 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search · 7 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 progressive shrinking on scale and refinement stages (ablation)EASNet-S (K=3,W=2,D=2,S=2) · Scene Flow testEPE (px): 1.8 -> 0.86Improved
add progressive shrinking over kernel, width and depth (ablation)EASNet sub-networks · Scene Flow testEPE (px)Improved
add progressive shrinking on scale and refinement beyond K-W-D (ablation)EASNet small sub-networks · Scene Flow testEPE (px): nearly 50% error reductionImproved
add progressive shrinking when shrinking width and depth (ablation)EASNet sub-networks · Scene Flow testEPE (px)Improved
increase scale from S=2 to S=4 (ablation)EASNet sub-network · Scene Flow testEPE (px)No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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