AI Paper Atlas

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

Coupling the Generator with Teacher for Effective Data-Free Knowledge Distillation

Xu Chen, Yang Li, Yahong Han, Guangquan Xu, Jialie Shen

ICCV 2025 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 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 feature-level alignment loss L_align to the generator (ablation)CPNet · CIFAR-100 (ResNet34->ResNet18)top-1 accuracy (%): 61.32 -> 76.56Improved
add feature-level adversarial loss L_adv (ablation)CPNet · CIFAR-10 (ResNet34->ResNet18)top-1 accuracy (%): 94.56 -> 94.63Improved
add feature MSE distillation loss at penultimate layer (ablation)CPNet · CIFAR-10 (ResNet34->ResNet18)top-1 accuracy (%): 94.63 -> 94.66No clear effect
use coupled generator instead of CMI generator (ablation)CPNet · CIFAR-10 (ResNet34->ResNet18)top-1 accuracy (%): 93.84 -> 94.48Improved
use coupled generator instead of noisy-layer generator (ablation)CPNet · CIFAR-100 (ResNet34->ResNet18)top-1 accuracy (%): 76.29 -> 76.45Improved
split teacher into 4 blocks instead of 1 or 8 (ablation)CPNet · CIFAR-10 (ResNet34->ResNet18)top-1 accuracy (%): 87.26 -> 94.66 (1 to 4 blocks); 94.66 -> 90.01 (4 to 8 blocks)Mixed
CPNet-300 vs NAYER-300 with same scheduleNAYER · TinyImageNet (ResNet34->ResNet18)top-1 accuracy (%): 64.17 -> 64.91Improved
use CPNet-100 for training efficiencyDFKD pipeline · CIFAR-10 (WRN40-2->WRN16-2)training time (hours): 1.80 -> 1.39 (vs NAYER-100)Improved

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