AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Beyond the Limits: Overcoming Negative Correlation of Activation-Based Training-Free NAS

Haidong Kang, Lianbo Ma, Pengjun Chen, Guo Yu, Xingwei Wang, Min Huang

ICCV 2025 · Architectures and efficiency › Neural architecture search · approach: One-shot and few-shot supernets · 0 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 stochastic activation masking (SAM) to SWAP (ablation)SWAP · NAS-Bench-201 ImageNet16-120test accuracy (%): 35.40 -> 42.48Improved
add non-linear rescaling (NIR) to SWAP (ablation)SWAP · NAS-Bench-201 ImageNet16-120test accuracy (%): 35.40 -> 44.49Improved
add both SAM and NIR to SWAP (ablation)SWAP · NAS-Bench-201 CIFAR-10test accuracy (%): 90.48 -> 93.68Improved
add both SAM and NIR to NWOT (ablation)NWOT · NAS-Bench-201 ImageNet16-120test accuracy (%): 42.31 -> 45.27Improved
add SAM only to NWOT (ablation)NWOT · NAS-Bench-201 ImageNet16-120test accuracy (%): 42.31 -> 42.93No clear effect
apply NCD to NWOT in the 77-convolution NAS-Bench-201 subspaceNWOT · NAS-Bench-201 subspace 77 (CIFAR-10)Spearman rho: -0.734 -> 0.679Improved
apply NCD to SWAP in the 77-convolution subspaceSWAP · NAS-Bench-201 subspace 77 (CIFAR-10)Spearman rho: -0.246 -> 0.715Improved
apply NCD in the 5-convolution subspaceSWAP and NWOT · NAS-Bench-201 subspace 5 (CIFAR-10)Spearman rho: 0.769 -> 0.765 (SWAP); 0.773 -> 0.747 (NWOT)Hurt
apply NCD to SWAP on NAS-Bench-201 CIFAR-10SWAP · NAS-Bench-201 CIFAR-10test accuracy (%): 90.48 -> 93.68Improved
vary SAM masking probability alpha (ablation)SWAP+SAM · NAS-Bench-201 CIFAR-10test accuracy (%): 90.48 (alpha=0) -> 93.15 (alpha=0.95) -> 93.05 (alpha=0.99)Mixed
vary alpha for NWOT+SAM+NIR (ablation)NWOT+SAM+NIR · NAS-Bench-201 CIFAR-10test accuracy (%): 93.48 (alpha=0) -> 94.00 (alpha=0.95) -> 93.30 (alpha=0.99)Mixed
apply NCD-NWOT to MobileNet-like space searchNCD-NWOT · MobileNet-like ImageNet1ktop-1 accuracy (%): 75.6 -> 78.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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