AI Paper Atlas

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

Classification-by-Components: Probabilistic Modeling of Reasoning over a Set of Components

Sascha Saralajew, Lars Holdijk, Maike Rees, Ebubekir Asan, Thomas Villmann

NeurIPS 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 18 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
replace ResNet-50 pooling and FC layer with CBC probabilistic reasoning headResNet-50 on ImageNet · ImageNetinference speed (images/sec): 369 -> 371 images/secNo clear effect
restrict number of components below number of classes (9 components) to force negative reasoning (ablation)CBC on MNIST · MNISTtest accuracy: 99.32 ± 0.09No clear effect
fixed uniform pixel probabilities instead of trainable alpha in spatial reasoning (ablation)patch-component CBC · MNISTtest accuracyNo 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