Research map / Label-efficient and robust learning / Domain adaptation and generalization
Neuron Coverage-Guided Domain Generalization
Chris Xing Tian, Haoliang Li, Xiaofei Xie, Yang Liu, Shiqi Wang
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 gradient similarity loss to coverage loss (ablation) | NCDG · PACS SSDG (Sketch source) | accuracy: 45.6 -> 53.1 | Improved |
| add coverage maximization loss to gradient similarity loss (ablation) | NCDG · PACS SSDG (Sketch source) | accuracy: 45.4 -> 53.1 | Improved |
| add gradient similarity loss to coverage loss (ablation) | NCDG · PACS SSDG (Cartoon source) | accuracy: 76.3 -> 76.4 | No clear effect |
| add gradient similarity loss to coverage loss (ablation) | NCDG · PACS SSDG (Photo source) | accuracy: 43.6 -> 49.0 | Improved |
| add coverage loss to Augmix | NCDG · CIFAR-10-C digital (avg) | accuracy: 76.6 -> 79.2 | Improved |
| add NCDG loss to adversarial augmentation GUD | GUD · Digits SSDG (avg) | accuracy: 54.6 -> 57.3 | Improved |
| add NCDG loss to M-ADA | M-ADA · Digits SSDG (avg) | accuracy: 59.5 -> 62.5 | Improved |
| add NCDG regularization over vanilla training on original and intensity-reversed data | Vanilla** · Digits SSDG (avg) | accuracy: 69.4 -> 73.4 | Improved |
| add coverage loss to DeepLabv3+ | DeepLabv3+ · GTA5 to Cityscapes | mIoU: 29.7 -> 34.7 | Improved |
| add coverage loss to DeepLabv3+ with ISW | RobustNet · GTA5 to Cityscapes | mIoU: 36.6 -> 37.2 | Improved |
| apply coverage loss on all ResNet-18 layer outputs instead of first conv only (ablation) | NCDG · PACS SSDG (Sketch source) | accuracy: 46.7 -> 53.1 | Improved |
| replace coverage loss with L1 regularization (ablation) | NCDG · PACS SSDG (Sketch source) | accuracy: 53.1 -> 46.1 | Hurt |
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.
- Augmix — AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty (ICLR 2020) · better on 1 of 1 shared result
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
- Improving Generalization With Domain Convex Game (CVPR 2023 · similarity 0.88)
- In Search of Lost Domain Generalization (ICLR 2021 · similarity 0.88)
- Episodic Training for Domain Generalization (ICCV 2019 · similarity 0.88)
- Gradient-Guided Annealing for Domain Generalization (CVPR 2025 · similarity 0.86)
- Is Large-scale Pretraining the Secret to Good Domain Generalization? (ICLR 2025 · similarity 0.86)
- Sharpness-Aware Model-Agnostic Long-Tailed Domain Generalization (AAAI 2024 · similarity 0.86)
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.
