AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Conditional Variational Capsule Network for Open Set Recognition

Yunrui Guo, Guglielmo Camporese, Wenjing Yang, Alessandro Sperduti, Lamberto Ballan

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 64 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 ResNet20 feature extractor before CapsNet (ablation)CVAECapOSR · SVHN vs CIFAR100, O=30.72%AUROC: 0.767 -> 0.949Improved
add CapsNet instead of FC layer (ablation)CVAECapOSR (ResNet20) · SVHN vs CIFAR100, O=30.72%AUROC: 0.595 -> 0.949Improved
add dynamic routing to CapsNet (ablation)CVAECapOSR (ResNet20) · SVHN vs CIFAR100, O=30.72%AUROC: 0.949 -> 0.954Improved
add dynamic routing to CapsNet (ablation)CVAECapOSR (ResNet20) · SVHN vs CIFAR100, O=0%AUROC: 0.981 -> 0.982No clear effect
add ResNet20 feature extractor before CapsNet (ablation)CVAECapOSR · SVHN vs CIFAR100, O=0%AUROC: 0.971 -> 0.981Improved
learn prior targets instead of fixing them (ablation)CVAECapOSR · CIFAR+50 unknown detectionAUROC: 0.829 -> 0.889Improved
learn prior targets instead of fixing them (ablation)CVAECapOSR · CIFAR+10 unknown detectionAUROC: 0.868 -> 0.888Improved
learn prior targets instead of fixing them (ablation)CVAECapOSR · MNIST unknown detectionAUROC: 0.997 -> 0.992Hurt
learn prior targets instead of fixing them (ablation)CVAECapOSR · SVHN unknown detectionAUROC: 0.953 -> 0.956No clear effect
add contrastive term (alpha=1.0 instead of 0.5) with margin 10 (ablation)CVAECapOSR · SVHN vs CIFAR100, O=30.72%AUROC: 0.564 -> 0.954Improved
increase margin m_k from 5.0 to 20.0 at alpha=0.5 (ablation)CVAECapOSR · SVHN vs CIFAR100, O=30.72%AUROC: 0.527 -> 0.947Improved
increase alpha from 1.0 to 2.0 at m_k=10.0 (ablation)CVAECapOSR · SVHN vs CIFAR100, O=30.72%AUROC: 0.954 -> 0.951No clear effect

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