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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add OCR as plug-and-play to source-free SHOT | SHOT · Office-Home (source-free) | accuracy: 71.8 -> 72.8 | Improved |
| 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 adaptation | TENT · CIFAR100-C online | test error (%): 34.4 -> 31.3 | Improved |
| add OCR to ResNet-18 for domain generalization | ResNet-18 · PACS | mean accuracy: 80.6 -> 85.5 | Improved |
| add Mixup or Manifold Mixup | ResNet-18 · PACS | mean accuracy: 80.6 -> 78.5 (Mixup), 76.2 (Manifold Mixup) | Hurt |
| add OCR to RobustNet | RobustNet · GTAV segmentation | mean mIoU: 35.1 -> 35.7 | No clear effect |
| apply OCR at deeper layers rather than input (ablation) | OCR · Office-Home | accuracy: 68.5 (Input) -> 72.8 (FC) | Improved |
| use annealed lambda instead of residual z_a - z_o (ablation) | OCR · PACS | mean accuracy: 84.0 -> 85.5 | Improved |
| add OCR for adversarial robustness against PGD | ERM · PACS PGD attack | mean accuracy: 38.4 -> 61.6 | Improved |
| remove ColorJitter from augmentations (ablation) | OCR · PACS | mean accuracy: 85.5 -> 83.4 when removed | Improved |
| add OCR order-preserving regularization vs prediction-based (ablation) | SHOT · Office-Home top-5 | top-5 accuracy: 90.2 -> 92.2 | Improved |
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.
- TENT — Tent: Fully Test-Time Adaptation by Entropy Minimization (ICLR 2021) · better on 2 of 2 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
- Co-regularized Alignment for Unsupervised Domain Adaptation (NeurIPS 2018 · similarity 0.86)
- Representation Enhancement-Stabilization: Reducing Bias-Variance of Domain Generalization (ECCV 2024 · similarity 0.86)
- Deja Vu: Continual Model Generalization for Unseen Domains (ICLR 2023 · similarity 0.85)
- Exploring Object Relation in Mean Teacher for Cross-Domain Detection (CVPR 2019 · similarity 0.85)
- CrossMatch: Cross-Classifier Consistency Regularization for Open-Set Single Domain Generalization (ICLR 2022 · similarity 0.85)
- Reducing Divergence in Batch Normalization for Domain Adaptation (AAAI 2025 · similarity 0.84)
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.
