AI Paper Atlas

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

Matching Guided Distillation

Kaiyu Yue, Jiangfan Deng, Feng Zhou

ECCV 2020 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 66 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 channel matching before AMP reduction (ablation)MGD-AMP, MobileNet-V2 · CUB-200 (IN-1K pre-trained student)top-1 error (%): 22.10 -> 20.64Improved
add channel matching before AMP reduction (ablation)MGD-AMP, ShuffleNet-V2 · CUB-200 (IN-1K pre-trained student)top-1 error (%): 27.62 -> 25.95Improved
use absolute max pooling instead of max pooling (ablation)MGD, MobileNet-V2 · CUB-200 (IN-1K pre-trained student)top-1 error (%): 21.63 -> 20.64Improved
use absolute max pooling instead of max pooling (ablation)MGD, ShuffleNet-V2 · CUB-200 (IN-1K pre-trained student)top-1 error (%): 26.20 -> 25.95Improved
use absolute max pooling instead of average pooling (ablation)MGD, MobileNet-V2 · CUB-200 (IN-1K pre-trained student)top-1 error (%): 22.19 -> 20.64Improved
use absolute max pooling instead of average pooling (ablation)MGD, ShuffleNet-V2 · CUB-200 (IN-1K pre-trained student)top-1 error (%): 27.27 -> 25.95Improved
update matching every 2 epochs instead of every epoch or every 4 (ablation)MGD-AMP, MobileNet-V2/ShuffleNet-V2 · CUB-200 (IN-1K pre-trained student)top-1 errorImproved
use AMP instead of sparse matching on CIFAR-100 (ablation)MGD, WRN s:28-2 · CIFAR-100 (from scratch)top-1 error (%): 21.22 -> 21.12Improved
use random drop instead of sparse matching (ablation)MGD, WRN s:28-2 · CIFAR-100 (from scratch)top-1 error (%): 21.22 -> 22.21Hurt
use MGD-AMP instead of Overhaul distillationResNet-18 RetinaNet · COCO val2017 RetinaNet 1x single-scaleAP bbox: 30.02 -> 31.15Improved
use MGD-AMP instead of Overhaul distillationShuffleNet-V2 student · CUB-200 (IN-1K pre-trained student)top-1 error (%): 27.42 -> 25.95Improved
use ImageNet pre-trained student instead of from scratchShuffleNet-V2 baseline · CUB-200 (IN-1K pre-trained student)top-1 error (%): 66.28 -> 31.39Improved

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