AI Paper Atlas

Research map / Architectures and efficiency / CNN design

CNN^{2}: Viewpoint Generalization via a Binocular Vision

Wei-Da Chen, Shan-Hung (Brandon) Wu

NeurIPS 2019 · Architectures and efficiency › CNN design · approach: Compact CNN architectures · 1 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
CNN2 binocular architecture instead of vanilla CNNCNN · ModelNet2D unseen viewpointsaccuracy: 0.907 -> 0.941Improved
CNN2 instead of vanilla CNNCNN · SmallNORB unseen viewpointsaccuracy: 0.722 -> 0.865Improved
CNN2 instead of vanilla CNNCNN · RGB-D Object unseen viewpointsaccuracy: 0.795 -> 0.868Improved
CNN2 instead of CapsuleNet for training speedCNN2 · SmallNORBtraining time (min): 1328 -> 121Improved
replace CNN2 blocks with Big-Little modules (CNN2+BL) (ablation)CNN2 · ModelNet2Daccuracy: 0.941 -> 0.918Hurt
replace CNN2 blocks with Big-Little modules (CNN2+BL) (ablation)CNN2 · RGB-D Objectaccuracy: 0.868 -> 0.778Hurt
tie weights of dual feedforward pathways (single pathway) (ablation)CNN2 · 3D viewpoint generalizationaccuracyHurt
drop parallax augmentation (ablation)CNN2 · 3D viewpoint generalizationaccuracyHurt
replace CM pooling with max pooling (ablation)CNN2 · 3D viewpoint generalizationaccuracyHurt
add CM pooling to vanilla CNNCNN · RGB-D ObjectaccuracyImproved
pool before convolution instead of after (ablation)CNN2 · 3D viewpoint generalizationaccuracyHurt
early or late fusion only instead of fusion at all layers (ablation)CNN2 · RGB-D ObjectaccuracyHurt

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