Research map / Label-efficient and robust learning / Domain adaptation and generalization
Probability Weighted Compact Feature for Domain Adaptive Retrieval
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 |
|---|---|---|---|
| Use PWCF rather than KSH | cross-domain retrieval · MNIST&USPS, 64 bits | MAP (%): 47.43 -> 51.75 | Helped |
| Use PWCF rather than KSH | cross-domain retrieval · VOC2007&Caltech101, 64 bits | MAP (%): 76.70 -> 79.31 | Helped |
| Use PWCF rather than KSH | cross-domain retrieval · Caltech256&ImageNet, 64 bits | MAP (%): 32.83 -> 35.24 | Helped |
| Use PWCF rather than KSH | Office-Home cross-domain retrieval · R→C, 64 bits | MAP (%): 18.51 -> 18.42 | Hurt |
| Add BP induced focal-triplet loss (ablation) | PWCF · MNIST&USPS cross-domain retrieval, 64 bits | MAP (%): 50.57 -> 51.75 | Helped |
| Replace standard triplet loss with focal-triplet loss (ablation) | PWCF · MNIST&USPS cross-domain retrieval, 64 bits | MAP (%): 50.01 -> 51.75 | Helped |
| Add manifold loss (ablation) | PWCF · MNIST&USPS cross-domain retrieval, 64 bits | MAP (%): 34.56 -> 51.75 | Helped |
| Add BP induced classification loss (ablation) | PWCF · MNIST&USPS cross-domain retrieval, 64 bits | MAP (%): 50.36 -> 51.75 | Helped |
| Use HFON rather than original features for cross-domain distances (ablation) | PWCF · MNIST&USPS cross-domain retrieval, 64 bits | MAP (%): 36.36 -> 51.75 | Helped |
| Add BP induced quantization loss (ablation) | PWCF · MNIST&USPS cross-domain retrieval, 64 bits | MAP (%): 10.60 -> 51.75 | Helped |
| Use PWCF rather than KSH | Office-Home cross-domain retrieval · average, 64 bits | MAP (%): 25.40 -> 29.11 | Helped |
Closest papers by meaning
- RoDA: Robust Domain Alignment for Cross-Domain Retrieval Against Label Noise (AAAI 2025 · similarity 0.88)
- Retrieval Across Any Domains via Large-scale Pre-trained Model (ICML 2024 · similarity 0.87)
- Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transport (AAAI 2024 · similarity 0.87)
- Semantic Feature Learning for Universal Unsupervised Cross-Domain Retrieval (NeurIPS 2024 · similarity 0.86)
- Effective Comparative Prototype Hashing for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.86)
- DiDA: Disambiguated Domain Alignment for Cross-Domain Retrieval with Partial Labels (AAAI 2024 · similarity 0.85)
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.