AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Zero-Shot Neural Network Evaluation With Sample-Wise Activation Patterns

Yameng Peng, Andy Song, Haytham M. Fayek, Vic Ciesielski, Xiaojun Chang

TPAMI 2026 · Architectures and efficiency › Neural architecture search · approach: One-shot and few-shot supernets · 8 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 Gaussian size regularisation to SWAP-Score (ablation)SWAP-Score · NB101 CIFAR-10Spearman correlation: 0.47 -> 0.75Improved
add Gaussian size regularisation to SWAP-Score (ablation)SWAP-Score · NB201 CIFAR-100Spearman correlation: 0.81 -> 0.90Improved
add Gaussian size regularisation to SWAP-Score (ablation)SWAP-Score · NB301 CIFAR-10Spearman correlation: 0.58 -> 0.63Improved
add the same regularisation to #Params (ablation)#Params · NB101 CIFAR-10Spearman correlation: 0.38 -> 0.76Improved
add the same regularisation to #Params (ablation)#Params · NB201 CIFAR-100Spearman correlation: 0.73 -> 0.73No clear effect
add the same regularisation to #FLOPs (ablation)#FLOPs · NB101 CIFAR-10Spearman correlation: 0.37 -> 0.76Improved
increase batch size from 8 to 128 (ablation)SWAP-Score · 1000 DARTS CNNs CIFAR-10Spearman correlation: 0.933 -> 0.649Hurt
increase batch size (ablation)SWAP-Score · 500 BERT-like Transformers GLUESpearman correlation: approximately 0.71No clear effect
increase input image dimension from 3x3x3 to 3x32x32 (ablation)SWAP-Score · 1000 DARTS CNNs CIFAR-10Spearman correlationImproved
replace CIFAR-10 images with Gaussian noise and increase dimension (ablation)SWAP-Score · 1000 DARTS CNNs CIFAR-10Spearman correlationHurt
use SWAP-Score instead of Attention Confidence for Transformerszero-shot proxy · GLUE 500 TransformersSpearman correlation: 0.666 -> 0.711Improved
use SWAP-NAS adaptive on ImageNet instead of mu=25 sigma=25SWAP-NAS · ImageNettop-1 test error: 24.0 -> 23.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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