AI Paper Atlas

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

Order-preserving Consistency Regularization for Domain Adaptation and Generalization

Mengmeng Jing, Xiantong Zhen, Jingjing Li, Cees G. M. Snoek

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 18 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
add OCR as plug-and-play to source-free SHOTSHOT · Office-Home (source-free)accuracy: 71.8 -> 72.8Improved
add representation-based consistency regularization (ablation)NRC and SHOT · Office-Home (source-free)accuracy: 71.8 -> 71.4 (SHOT)Hurt
add OCR to TENT in online test-time adaptationTENT · CIFAR100-C onlinetest error (%): 34.4 -> 31.3Improved
add OCR to ResNet-18 for domain generalizationResNet-18 · PACSmean accuracy: 80.6 -> 85.5Improved
add Mixup or Manifold MixupResNet-18 · PACSmean accuracy: 80.6 -> 78.5 (Mixup), 76.2 (Manifold Mixup)Hurt
add OCR to RobustNetRobustNet · GTAV segmentationmean mIoU: 35.1 -> 35.7No clear effect
apply OCR at deeper layers rather than input (ablation)OCR · Office-Homeaccuracy: 68.5 (Input) -> 72.8 (FC)Improved
use annealed lambda instead of residual z_a - z_o (ablation)OCR · PACSmean accuracy: 84.0 -> 85.5Improved
add OCR for adversarial robustness against PGDERM · PACS PGD attackmean accuracy: 38.4 -> 61.6Improved
remove ColorJitter from augmentations (ablation)OCR · PACSmean accuracy: 85.5 -> 83.4 when removedImproved
add OCR order-preserving regularization vs prediction-based (ablation)SHOT · Office-Home top-5top-5 accuracy: 90.2 -> 92.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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