AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

CoDiNet: Path Distribution Modeling With Consistency and Diversity for Dynamic Routing

Huanyu Wang, Zequn Qin, Songyuan Li, Xi Li

TPAMI 2021 · Architectures and efficiency › RNNs and normalization · approach: Efficient network compression and training · 8 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 consistency loss to vanilla dynamic routing (ablation)Vanilla dynamic routing ResNet-110 · CIFAR-10accuracy: 93.66 -> 92.88Hurt
add diversity loss to vanilla dynamic routing (ablation)Vanilla dynamic routing ResNet-110 · CIFAR-10accuracy: 93.66 -> 91.34Hurt
add both consistency and diversity losses (ablation)Vanilla dynamic routing ResNet-110 · CIFAR-10accuracy: 93.66 -> 94.47Improved
set diversity margin to 0.5 instead of 0.25 (ablation)CoDiNet ResNet-110 · CIFAR-10accuracy: 93.12 -> 94.47Improved
increase diversity margin from 0.5 to 0.75 (ablation)CoDiNet ResNet-110 · CIFAR-10accuracy: 94.47 -> 92.75Hurt
increase diversity margin from 0.5 to 1.00 (ablation)CoDiNet ResNet-110 · CIFAR-10accuracy: 94.47 -> 92.46Hurt
use CoDiNet instead of ResNet-110ResNet-110 · CIFAR-10accuracy: 93.60 -> 94.47Improved
use CoDiNet instead of vanilla dynamic routingResNet-110 · CIFAR-100accuracy: 70.3 -> 72.9Improved
use CoDiNet instead of vanilla dynamic routingResNet-110 · SVHNaccuracy: 93.15 -> 94.28Improved
use CoDiNet-50 instead of ResNet-50ResNet-50 · ImageNettop-1 accuracy: 75.36 -> 76.63Improved
raise cost weight gamma from 0.01 to 0.10 (ablation)CoDiNet ResNet-110 · CIFAR-10accuracy: 94.47 -> 92.45Hurt
use CoDiNet instead of vanilla dynamic routingResNet-32 · CIFAR-10accuracy: 91.55 -> 92.48Improved

Later papers that compared with this method

1 later accepted paper reports CoDiNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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