AI Paper Atlas

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

iCaps: An Interpretable Classifier via Disentangled Capsule Networks

Dahuin Jung, Jonghyun Lee, Jihun Yi, Sungroh Yoon

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 15 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
use iCaps instead of ResNet-18 classifieriCaps · MNISTaccuracy of p(y|c): 0.992 -> 0.992No clear effect
use iCaps instead of DeepCapsiCaps · SVHNaccuracy of p(y|c): 0.971 -> 0.920Hurt
use iCaps instead of ResNet-18iCaps · CelebAaccuracy of p(y|c): 0.977 -> 0.984Improved
use class-relevant intra-class variation in c (iCaps) instead of LORDdisentanglement · SVHNaccuracy of p(y|r): 0.163 -> 0.099Improved
use iCaps instead of ML-VAEdisentanglement · MNISTaccuracy of p(y|r): 0.717 -> 0.099Improved
use iCaps instead of Cycle-VAEdisentanglement · CelebAaccuracy of p(y|r): 0.793 -> 0.501Improved
add L_concept loss (ablation)iCaps · MNIST/SVHN/CelebAmutual information I(c;y)Improved
add concept-distinctness discriminator D_CR (ablation)iCaps · MNISTdistinctness of class capsule elementsImproved

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