AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Deeply-Supervised Knowledge Synergy

Dawei Sun, Anbang Yao, Aojun Zhou, Hao Zhao

CVPR 2019 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 91 citations (OpenAlex)

Check 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 pairwise knowledge synergy to deep supervisionResNet-18 · ImageNet validationTop-1 error: 30.46 -> 28.68Improved
Add pairwise knowledge synergy to deep supervisionResNet-32 · CIFAR-100 testerror: 29.89 -> 26.81Improved
Use simple AP+2FC auxiliary classifiers instead of the designed branches (ablation)ResNet-32 DKS · CIFAR-100 testerror: 29.89(0.26) -> 35.09(0.54)Hurt
Use AP+1Conv+2FC auxiliary classifiers instead of the designed branches (ablation)ResNet-32 DKS · CIFAR-100 testerror: 30.24(0.05) -> 32.52(0.27)Hurt
Use narrow auxiliary blocks (ablation)ResNet-32 DKS · CIFAR-100 testerror: 29.52(0.30) -> 29.18(0.28)Improved
Use shallow auxiliary blocks (ablation)ResNet-32 DKS · CIFAR-100 testerror: 29.39(0.09) -> 28.69(0.28)Improved
Add a classifier at C4 to the C2+C3 arrangement (ablation)ResNet-18 DKS · ImageNet validationTop-1 error: 28.68 -> 29.00Hurt
Use bidirectional rather than top-down matching (ablation)ResNet-18 DKS · ImageNet validationTop-1 accuracy gain over baseline: +0.50% -> +2.38%Improved
Use bidirectional rather than bottom-up matching (ablation)ResNet-18 DKS · ImageNet validationTop-1 accuracy gain over baseline: +2.22% -> +2.38%Improved
Add three auxiliary classifiers rather than one (ablation)ResNet-18 DKS · ImageNet validationTop-1 error: 31.06 -> 28.68Improved
Add a single classifier at an earlier layer rather than a deeper layer (ablation)ResNet-18 DKS · ImageNet validationTop-1 error: 30.69 -> 31.89Improved
Use DKS rather than DS on noisy CIFAR-10 with 50% corrupted labels (ablation)DenseNet-40, k=12 · CIFAR-10, 50% corrupted training labelsaccuracy: 80.47% -> 83.73%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