AI Paper Atlas

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

Domain Decorrelation with Potential Energy Ranking

Sen Pei, Jiaxi Sun, Richard Yi Da Xu, Shiming Xiang, Gaofeng Meng

AAAI 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 2 citations (OpenAlex)

Read the paper

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 PoER ranking and cluster regularization (ablation)ResNet-18 with GCPL classification · PACStop-1 accuracy: 81.86 -> 84.18Improved
add shallow-layer ranking loss (ablation)ResNet-18 with GCPL classification · PACStop-1 accuracy: 81.86 -> 83.72Improved
add deeper-layer cluster loss (ablation)ResNet-18 with GCPL classification · PACStop-1 accuracy: 81.86 -> 82.60Improved
add ranking loss alongside cluster loss (ablation)PoER with cluster loss only · PACStop-1 accuracy: 82.60 -> 84.18Improved
set regularization weight α to 0.2 rather than 0.0 (ablation)PoER · PACStop-1 accuracy: 81.86 -> 84.20Improved
increase prototype count from 1 to 10 (ablation)PoER · PACStop-1 accuracy: 82.40 -> 84.21Improved
use PoER instead of GCPLResNet-18 · PACS Avg.top-1 accuracy: 81.86 -> 84.18Improved
use PoER instead of DDAIGResNet-18 · Office-Home Avg.top-1 accuracy: 65.5 -> 66.6Improved
use PoER instead of DDAIGResNet-18 · Digits-DG Avg.top-1 accuracy: 77.6 -> 81.8Improved
use PoER instead of StableNetdomain generalization method · VLCS Avg.top-1 accuracy: 77.65 -> 76.63Hurt
use PoER rather than the vanilla ResNet-18 (ablation)ResNet-18 · NICOtop-1 accuracy: 51.71 -> 62.62Improved
add PoER to convolutional and attention-based backbones (ablation)ResNet-50, DenseNet-121, and Swin-T · NICOtop-1 accuracyImproved

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