AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP"

Jihao Liu, Xin Huang, Guanglu Song, Hongsheng Li, Yu Liu

ECCV 2022 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS

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
search over convolution, transformer and MLP operators (vs convolution only) (ablation)UniNet-B0 · ImageNet-1K val (ablation)top-1 accuracy (%): 77.7 -> 79.1Improved
search DSM per stage (vs L-DSM in all stages) (ablation)UniNet-B0 · ImageNet-1K val (ablation)top-1 accuracy (%): 78.5 -> 79.1Improved
search DSM per stage (vs G-DSM in all stages) (ablation)UniNet-B0 · ImageNet-1K val (ablation)top-1 accuracy (%): 76.8 -> 79.1Improved
search DSM per stage (vs LG-DSM in all stages) (ablation)UniNet-B0 · ImageNet-1K val (ablation)top-1 accuracy (%): 78.9 -> 79.1Improved
add context-aware DSMs to PVT-Tiny (ablation)PVT-Tiny · ImageNet-1K valtop-1 accuracy (%): 75.1 -> 77.5Improved
add context-aware DSMs to Swin-T (ablation)Swin-T · ImageNet-1K valtop-1 accuracy (%): 81.2 -> 81.6Improved
stack MLP-Mixer blocks before ViT blocks (MLP-ViT) instead of pure ViT (ablation)ViT · ImageNet-1K val (pilot, operator stacking)top-1 accuracy (%): 78.0 -> 77.8No clear effect
stack ViT blocks before MLP blocks (ViT-MLP) instead of pure ViT (ablation)ViT · ImageNet-1K val (pilot, operator stacking)top-1 accuracy (%): 78.0 -> 76.5Hurt
use pure MLP-Mixer instead of ViT (ablation)ViT · ImageNet-1K val (pilot, operator stacking)top-1 accuracy (%): 78.0 -> 76.8Hurt

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