AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillation

Utkarsh Nath, Yan-Cheng Wang, Pavan K. Turaga, Yingzhen Yang

IJCV 2024 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 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 robust teacher with cross-layer distillation (RNAS-CL) vs standard training (ablation)S3 search space · CIFAR-10 (no adversarial training)PGD-20 accuracy: 17.69 -> 34.3Improved
add robust teacher with cross-layer distillation (RNAS-CL) vs standard training (ablation)S5 search space · CIFAR-10 (no adversarial training)PGD-20 accuracy: 18.44 -> 35.59Improved
add robust teacher with cross-layer distillation (RNAS-CL) vs standard training (ablation)S7 search space · CIFAR-10 (no adversarial training)PGD-20 accuracy: 19.3 -> 37.24Improved
add robust teacher with cross-layer distillation (RNAS-CL) vs standard training (ablation)S3 search space · CIFAR-10 (no adversarial training)clean accuracy: 89.92 -> 89.4No clear effect
use WRT-34 teacher instead of ResNet-18 teacher (ablation)RNAS-CL-S3 · CIFAR-10 (no adversarial training)PGD-20 accuracy: 26.35 -> 34.3Improved
use ResNet-50 teacher instead of ResNet-18 teacher (ablation)RNAS-CL-S3 · CIFAR-10 (no adversarial training)PGD-20 accuracy: 26.35 -> 35.76Improved
add TRADES adversarial retrainingRNAS-CL-M-WRT-34 · CIFAR-10 (no adversarial training)PGD-20 accuracy: 39.84 -> 51.76Improved
add TRADES adversarial retrainingRNAS-CL-M-WRT-34 · CIFAR-10 (no adversarial training)clean accuracy: 92.46 -> 87.29Hurt
add TRADES adversarial retrainingRNAS-CL-I-R-50 · ImageNet-100PGD-20 accuracy: 8.3 -> 32.44Improved
add TRADES adversarial retrainingRNAS-CL-I-R-50 · ImageNet-100clean accuracy: 85.98 -> 79.95Hurt
use RNAS-CL-WRT-50 instead of ResNet-50-Radversarially trained ImageNet model · ImageNet (FastAT)PGD-10 accuracy: 31.14 -> 33.30Improved
use RNAS-CL-S3-WRT-34 instead of MVV2-ARDnon-adversarially trained CIFAR-10 · CIFAR-10clean accuracy: 76.13 -> 89.4Improved

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