AI Paper Atlas

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

DistPro: Searching a Fast Knowledge Distillation Process via Meta Optimization

Xueqing Deng, Dawei Sun, Shawn Newsam, Peng Wang

ECCV 2022 · Label-efficient and robust learning › Knowledge distillation · approach: Distillation with causal and adaptive guidance · 7 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
learn searched distillation process alpha instead of equal pathway weights (ablation)DistPro · CIFAR100 (ResNet32x4 -> ShuffleNet-v1)top-1 accuracy (%): 73.54 -> 77.18Improved
learn searched distillation process alpha instead of equal pathway weights (ablation)DistPro · CIFAR100 (WRN-40-2 -> ShuffleNet-v1)top-1 accuracy (%): 74.28 -> 77.24Improved
use time-varying process instead of final alpha_T only (ablation)DistPro · CIFAR100 (ResNet56 -> ResNet20)top-1 accuracy (%): 71.24 -> 72.03Improved
use time-varying process instead of final alpha_T only (ablation)DistPro · CIFAR100 (ResNet32x4 -> ShuffleNet-v2)top-1 accuracy (%): 76.64 -> 77.54Improved
use time-varying process instead of final alpha_T only (ablation)DistPro · CIFAR100 (WRN-40-2 -> ShuffleNet-v1)top-1 accuracy (%): 77.19 -> 77.24No clear effect
use DistPro process instead of ReviewKD fixed pathwaysReviewKD · CIFAR100 (ResNet56 -> ResNet20)top-1 accuracy (%): 71.89 -> 72.03Improved
use searched process instead of equal weights alongside IFVD (ablation)DistPro · CityScapesmIoU (%): 68.49 -> 69.12Improved
use searched process instead of equal weights (ablation)DistPro · NYUv2 depthRMSE: 0.2030 -> 0.1972Improved
use biased softmax normalization instead of sigmoid (ablation)DistPro · CIFAR100 (WRN-28-4 -> WRN-16-4)accuracy (%): 78.80 -> 79.78Improved
use biased softmax normalization instead of plain softmax (ablation)DistPro · CIFAR100 (WRN-28-4 -> WRN-16-4)accuracy (%): 79.41 -> 79.78Improved
use DistPro instead of ReviewKD at short training of 10 epochsMobileNet student · ImageNet1K (ResNet-50 -> MobileNet, 10 epochs)top-1 accuracy (%): 62.03 -> 65.25Improved
use DistPro instead of ReviewKD at 100 epochsMobileNet student · ImageNet1K (ResNet-50 -> MobileNet, 100 epochs)top-1 accuracy (%): decreased to 0.14%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