Research map / Label-efficient and robust learning / Domain adaptation and generalization
Compact Feature Learning for Multi-Domain Image Classification
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 orthogonal regularization between private features across domains (ablation) | JARN / JOARN · MNIST | accuracy (%): 96.56 -> 97.10 | Helped |
| Add orthogonal regularization between private features across domains (ablation) | JARN / JOARN · MNIST-M | accuracy (%): 88.54 -> 89.34 | Helped |
| Add orthogonal regularization between private features across domains (ablation) | JARN / JOARN · VLCS pair 1: VOC2007 | accuracy (%): 79.31 -> 80.00 | Helped |
| Add orthogonal regularization between private features across domains (ablation) | JARN / JOARN · VLCS pair 1: SUN09 | accuracy (%): 81.03 -> 81.54 | Helped |
| Add orthogonal regularization between private features across domains (ablation) | JARN / JOARN · VLCS pair 2: VOC2007 | accuracy (%): 78.62 -> 79.41 | Helped |
| Add orthogonal regularization between private features across domains (ablation) | JARN / JOARN · VLCS pair 2: LabelMe | accuracy (%): 74.5 -> 76.13 | Helped |
| Add orthogonal regularization between private features across domains (ablation) | JARN / JOARN · VLCS pair 3: SUN09 | accuracy (%): 78.70 -> 80.02 | Helped |
| Add orthogonal regularization between private features across domains (ablation) | JARN / JOARN · VLCS pair 3: LabelMe | accuracy (%): 74.13 -> 75.75 | Helped |
| Add orthogonal regularization between private features across domains (ablation) | JARN / JOARN · PACS pair 1: Cartoon | accuracy (%): 92.65 -> 93.35 | Helped |
| Add orthogonal regularization between private features across domains (ablation) | JARN / JOARN · PACS pair 1: Art painting | accuracy (%): 89.00 -> 89.97 | Helped |
| Add orthogonal regularization between private features across domains (ablation) | JARN / JOARN · PACS pair 2: Cartoon | accuracy (%): 92.93 -> 93.21 | Helped |
| Add orthogonal regularization between private features across domains (ablation) | JARN / JOARN · PACS pair 2: Sketch | accuracy (%): 92.44 -> 93.12 | Helped |
Closest papers by meaning
- Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation (AAAI 2019 · similarity 0.89)
- Visual Representation Learning over Latent Domains (ICLR 2022 · similarity 0.87)
- Multivariate Regression on the Grassmannian for Predicting Novel Domains (CVPR 2016 · similarity 0.87)
- Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation (ICLR 2020 · similarity 0.87)
- Structure-Aware Feature Fusion for Unsupervised Domain Adaptation (AAAI 2020 · similarity 0.87)
- Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning (CVPR 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.