AI Paper Atlas

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

Mixing Configurations for Downstream Prediction

Juntang Wang, Hao Wu, Yihan Wang, Dongmian Zou, Shixin Xu

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias

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 energy statistics to the selector (ablation)MixConfig · CIFAR-100Top-1 accuracy: .738 -> .758Improved
add energy statistics to the selector (ablation)MixConfig · BBBPaccuracy: .882 -> .903Improved
add sample context h to the selector (ablation)MixConfig · CIFAR-100Top-1 accuracy: .747 -> .758Improved
add cluster embeddings to the selector (ablation)MixConfig · CIFAR-100Top-1 accuracy: .743 -> .758Improved
use all m configurations instead of only 2 (coarsest + finest) (ablation)MixConfig · CIFAR-100Top-1 accuracy: .716 -> .758Improved
use 6 vs all configurations (ablation)MixConfig · BBBPaccuracy: .895 -> .903Improved
replace configurations with random partitions of same dimensionality (ablation)MixConfig features · CIFAR-100Top-1 accuracy: .742 -> .737Hurt
learn per-sample adaptive weights instead of global learnable weights (ablation)MixConfig · BBBPaccuracy: .878 -> .903Improved
use the energy-aware selector instead of a stronger 2-layer MLP fusion head (ablation)configuration features · BBBPaccuracy: .884 -> .903Improved
add CSPA consensus clustering (ablation)Base · CIFAR-100Top-1 accuracy: .742 -> .743No clear effect
add DeepCluster single-resolution k-means featuresBase · OpenML-CC18 multi-class, CIFAR-100, MolHIVaccuracy / AUC: .782 -> .779 (multi-class)Hurt
replace linear probe with 2-layer MLP probe (ablation)CLIP on CIFAR-100 · CIFAR-100Top-1 accuracy: .742 -> .753Improved

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