AI Paper Atlas

Research map / Continual learning / Class-incremental

AdaPrior: Bayesian-Inspired Adaptive Prior Correction for Long-Tailed Continual Learning

S Divakar Bhat, Amit Popat More, Mudit Soni, Bhuvan Aggarwal

CVPR 2026 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning

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 post-hoc AdaPrior correction after training with AdaPrior Loss (Full AdaPrior) (ablation)AdaPrior Loss · CIFAR100-LT shuffled LFH 5 tasksaverage incremental accuracy: 40.97 -> 43.31Improved
add AdaPrior Loss to LUCIR+CE (ablation)LUCIR+CE · ImageNet-subset-LT shuffled LFH 10 tasksaverage incremental accuracy: 48.98 -> 58.21Improved
add post-hoc correction on top of AdaPrior Loss in ordered ImageNet-subset LFH (ablation)AdaPrior Loss · ImageNet-subset ordered LFH 10 tasksaverage incremental accuracy: 61.34 -> 61.23No clear effect
estimate priors dynamically (AdaPrior post-hoc) instead of static class frequency (logN) (ablation)LUCIR+CE · CIFAR100-LT shuffled 5 tasksaverage incremental accuracy: 42.37 (logN) vs 42.08 (AdaPrior post-hoc)No clear effect
estimate priors dynamically (AdaPrior post-hoc) instead of static class frequency (logN) (ablation)LUCIR+CE · ImageNet-subset-LT shuffled 10 tasksaverage incremental accuracy: 55.03 -> 56.27Improved
remove mixup from the training pipeline (ablation)Full AdaPrior · CIFAR100-LT shuffled 5 tasksaverage incremental accuracy: 43.31 -> 41.83Hurt
add AdaPrior post-hoc calibrationLUCIR+CE · ImageNet-subset-LT shuffled 5 tasksmean ECE: 0.1500 -> 0.1322Improved
set EMA momentum gamma near 0.05 (ablation)AdaPrior · hyperparameter studyaccuracyImproved
raise post-hoc correction weight alpha to about 0.6-0.7 (ablation)AdaPrior post-hoc · hyperparameter studyaccuracyMixed
apply post-hoc AdaPrior to PODNet backbone without tuningPODNet · CIFAR100-LT and ImageNet-LTaccuracy: +1-3%Improved
reduce exemplars per class from 20 to 5 (ablation)AdaPrior · ImageNet-subset-LT LFHaccuracyNo 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