AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Adaptive Bayesian Early-Exit Networks for Efficient Non-Transferable Learning

Siyu Luan, Yan Li, Zhong Chen, Zhenyi Wang

CVPR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing

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
set target-loss weight β=1 instead of β=0 (no target term) (ablation)ENL-DEE · Office-Home, Real-World source (ViT)PG: 0.00 -> 16.94Improved
raise β from 1 to 2 (ablation)ENL-DEE · Office-Home, Real-World source (ViT)PG: 16.94 -> 9.94Hurt
raise β from 1 to 3 (ablation)ENL-DEE · Office-Home, Real-World source (ViT)PG: 16.94 -> -1.99Hurt
use two-linear-layer exit heads at blocks 3,6,9,11 vs three-layer heads (ablation)ENL-DEE · PACS, sketch source (ViT)PG: 23.59 vs 19.96No clear effect
move exit placement to blocks 2,5,8,10 (ablation)ENL-DEE · PACS, sketch source (ViT)PG: 23.59 -> 19.98No clear effect
use ENL-DEE instead of NTL with ViTENL-DEE · CIFAR-10 source (ViT)PG: 44.9 -> 50.5Improved
use ENL-DEE instead of NTL with ResNet-34ENL-DEE · CIFAR-10 source (ResNet-34)PG: 54.9 -> 51.7Hurt
use ENL-DEE instead of CUTI with ResNet-34ENL-DEE · STL-10 source (ResNet-34)PG: 13.7 -> 38.9Improved
use ENL-DEE instead of NTL on PACSENL-DEE · PACS, sketch source (ViT)PG: -0.12 -> 23.59Improved
use ENL-DEE instead of NTL on DomainNetENL-DEE · DomainNet, quickdraw source (ResNet-34)PG: -38.75 -> 0.49Improved

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