AI Paper Atlas

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

REDistill: Robust Estimator Distillation for Balancing Robustness and Efficiency

Ondrej Tybl, Lukas Neumann

ECCV 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Distillation with causal and adaptive guidance · 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
replace KL with power divergence (lambda=2/3) in DKD-style lossDKD · CIFAR-100 (model-agnostic, ResNet32x4->SHN-V2)top-1 acc: 77.01 -> 77.52Improved
replace KL with power divergence (lambda=2/3)DKD · CIFAR-100 (model-agnostic, WRN-40-2->ResNet8x4)top-1 acc: 75.50 -> 77.21Improved
add REDistill loss to KDKD · CIFAR-100 (model-specific, ResNet32x4->SHN-V2)top-1 acc: 74.45 -> 74.99Improved
add REDistill loss to MLKDMLKD · CIFAR-100 (model-specific, ResNet32x4->SHN-V2)top-1 acc: 78.44 -> 78.82Improved
add REDistill loss to MLKDMLKD · CIFAR-100 (model-specific, VGG13->VGG8)top-1 acc: 75.18 -> 75.24Improved
use lambda 2/3 instead of 0 (KL) (ablation)REDistill · CIFAR-100 ResNet32x4->SHN-V2top-1 acc: 77.11 -> 77.52Improved
use lambda 2/3 vs 1 (ablation)REDistill · CIFAR-100 ResNet32x4->SHN-V2top-1 acc: 77.52 vs 77.50No clear effect
increase lambda to 2 (ablation)REDistill · CIFAR-100 ResNet32x4->SHN-V2top-1 acc: 77.52 -> 76.31Hurt
use REDistill vs best baseline on VGG13->VGG8 (model-agnostic)REDistill · CIFAR-100 VGG13->VGG8top-1 acc: 74.78 vs LSKD 74.61; RLD 74.40 in model-agnostic, but 74.88 vs RLD 74.93 in model-specificMixed
REDistill vs RLD on ResNet110->ResNet20 (model-agnostic)REDistill · CIFAR-100top-1 acc: 71.60 vs LSKD 71.67Mixed

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