AI Paper Atlas

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

Condensed Data Expansion Using Model Inversion for Knowledge Distillation

Kuluhan Binici, Shivam Aggarwal, Cihan Acar, Nam Trung Pham, Karianto Leman, Gim Hee Lee, Tulika Mitra

AAAI 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 1 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
guide model inversion with condensed samples via feature discriminatorFast · CIFAR-100 (WRN-40-2 -> MobileNet-v2)student accuracy: 48.21 -> 60.86Improved
guide model inversion with condensed samples via feature discriminatorCMI · CIFAR-100 (WRN-40-2 -> MobileNet-v2)student accuracy: 59.04 -> 68.05Improved
guide model inversion with condensed samples via feature discriminatorCMI · CIFAR-10 (ResNet-34 -> ResNet-18)student accuracy: 94.84 -> 94.97No clear effect
guide model inversion with condensed samples via feature discriminatorPRE-DFKD · CIFAR-100 (ResNet-34 -> MobileNet-v2)student accuracy: 66.56 -> 67.39Improved
naively add condensed samples to MI synthetic set (no feature alignment) (ablation)Fast · CIFAR-10 (ResNet-34 -> ResNet-18)student accuracy: 92.62 -> 92.72No clear effect
naively add condensed samples to MI synthetic set (no feature alignment) (ablation)CMI · CIFAR-100 (ResNet-34 -> ResNet-18)student accuracy: 77.04 -> 77.04No clear effect
naively add condensed samples to MI synthetic set (no feature alignment) (ablation)Fast · CIFAR-100 (ResNet-34 -> MobileNet-v2)student accuracy: 54.62 -> 56.57Improved
replace condensation method (DSA/DM/MTT) (ablation)Fast* (ours) · CIFAR-10 (ResNet-34 -> MobileNet-v2)student accuracy: 88.05 / 87.82 / 87.11 vs naive 86.37 / 86.54 / 86.78Improved
use real few-shot samples instead of condensed ones (ablation)PRE-DFKD* · CIFAR-100 (ResNet-34 -> MobileNet-v2)student accuracy: 67.39 -> 71.63Improved
use real few-shot samples instead of condensed ones (ablation)PRE-DFKD* · CIFAR-10 (ResNet-34 -> MobileNet-v2)student accuracy: 86.89 -> 86.77No clear effect
replace few-shot KD with expansion via model inversionPRE-DFKD* vs FSKD · CIFAR-10 (75% pruned VGG-11)student accuracy: 36.00 -> 68.48Improved
replace few-shot KD with expansion via model inversionPRE-DFKD* vs NetGraft · CIFAR-100 (VGG-16 -> ResNet-18, 1 spc)student accuracy: 55.51 -> 68.54Improved

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