AI Paper Atlas

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

Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation

Kien Do, Hung Le, Dung Nguyen, Dang Nguyen, HARIPRIYA HARIKUMAR, Truyen Tran, Santu Rana, Svetha Venkatesh

NeurIPS 2022 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 18 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 EMA generator samples to student training (MAD vs ABM generator-only)MAD · ImageNet (AlexNet)accuracy (%): 41.23 -> 45.48Improved
add EMA generator samples to student training (vs ABM)MAD · CIFAR100 (WRN)accuracy (%): 62.59 -> 64.05Improved
add EMA generator samples to student training (vs ABM)MAD · TinyImageNetaccuracy (%): 59.75 -> 62.32Improved
use EMA generator instead of memory bank of past synthetic samples (DFKD-Mem)MAD · ImageNet (AlexNet)accuracy (%): 43.30 -> 45.48Improved
use memory bank of past samples instead of generator-only (DFKD-Mem vs ABM)ABM · CIFAR100 (WRN)accuracy (%): 62.59 -> 61.25Hurt
set lambda_0=0 (drop samples from generator G, keep EMA only) (ablation)MAD · CIFAR100accuracyHurt
reduce either lambda_0 or lambda_1 below 1 (ablation)MAD · CIFAR100accuracyHurt
increase EMA momentum alpha to 1.0 (ablation)MAD · CIFAR100accuracy: about 50%Hurt
increase momentum alpha up to 0.95 (then too large at 0.999) (ablation)MAD · CIFAR100accuracyMixed
increase number of student update steps (ablation)MAD · CIFAR100accuracyImproved
MAD vs CMI on WRN teacher/studentMAD · CIFAR100 (WRN)accuracy (%): 68.75 -> 64.05Hurt

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