AI Paper Atlas

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

Deep Combinatorial Aggregation

Yuesong Shen, Daniel Cremers

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 4 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
train DCWA with consistency enforcing loss instead of NLL (ablation)DCWA · CIFAR-10NLL: 0.2651 -> 0.2355Improved
train DCWA with consistency enforcing loss instead of NLL (ablation)DCWA · CIFAR-10ECE: 0.0365 -> 0.0301Improved
train modelwise DCA with consistency enforcing loss instead of NLL (ablation)Modelwise DCA · CIFAR-10NLL: 0.1601 -> 0.1550Improved
train modelwise DCA with consistency enforcing loss instead of NLL (ablation)Modelwise DCA · CIFAR-10accuracy: 0.9495 -> 0.9481Hurt
train trunkwise DCA with consistency enforcing loss instead of NLL (ablation)Trunkwise DCA · CIFAR-10NLL: 0.1676 -> 0.1728Hurt
use SWA-like weight averaging DCWA vs SWADCWA · CIFAR-10accuracy: 0.9327 -> 0.9337No clear effect
DCWA vs standard trainingDCWA · CIFAR-10accuracy: 0.9264 -> 0.9337Improved
DCWA vs standard trainingDCWA · SVHNNLL: 0.1786 -> 0.1713Improved
modelwise DCA vs deep ensembleModelwise DCA · CIFAR-10NLL: 0.1746 -> 0.1550Improved
trunkwise DCA vs deep ensembleTrunkwise DCA · CIFAR-10NLL: 0.1746 -> 0.1676Improved
trunkwise DCA vs deep ensemble on CIFAR-10-CTrunkwise DCA · CIFAR-10-CBrier and ECEHurt
coarser component granularity in DCA (ablation)DCA · CIFAR-10accuracy, NLL, ECEImproved

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