AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

AutoDispNet: Improving Disparity Estimation With AutoML

Tonmoy Saikia, Yassine Marrakchi, Arber Zela, Frank Hutter, Thomas Brox

ICCV 2019 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 80 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
replace DispNet-C with architecture found by Dense-DARTSDispNet-C · Sintel clean (train)EPE: 3.19 -> 2.85Improved
tune learning rate and weight decay with BOHB (ablation)AutoDispNet-C · Sintel clean (train)EPE: 2.85 -> 2.66Improved
tune learning rate and weight decay with BOHB (ablation)AutoDispNet-C · FlyingThings3D testEPE: 1.53 -> 1.51No clear effect
stack a refinement network (CS) with Dense-DARTSAutoDispNet-C · Sintel clean (train)EPE: 2.85 -> 2.30Improved
add a second refinement network (CSS)AutoDispNet-CS · Sintel clean (train)EPE: 2.30 -> 2.14Improved
tune hyperparameters with BOHB (ablation)AutoDispNet-CSS · Sintel clean (train)EPE: 2.14 -> 1.97Improved
use AutoDispNet-cs (2 nets) instead of DispNet-CSS (3 nets)DispNet-CSS · Sintel clean (train)EPE: 2.36 -> 2.30Improved
shrink C_init to 18 (css) (ablation)AutoDispNet-CSS · Sintel clean (train)EPE: 2.14 -> 2.54Hurt
learn new cells for refinement network with Dense-DARTS (ablation)AutoDispNet-CS · Sintel clean (train)EPE: 2.30 -> 2.32No clear effect
tune new hyperparameters for refinement network with BOHB (ablation)AutoDispNet-CS with BOHB · Sintel clean (train)EPE: 2.14 -> 2.16No clear effect
replace Laina et al. with Dense-DARTS networkLaina et al. · SUN3D single-view depthAbs. rel: 0.272 -> 0.234Improved
replace Laina et al. with BOHB-tuned Dense-DARTS networkLaina et al. · NYU-Depth-V2Abs. rel: 0.127 -> 0.170Hurt

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