Research map / Label-efficient and robust learning / Domain adaptation and generalization
Prototype-Based Semantic Consistency Alignment for Domain Adaptive Retrieval
Tianle Hu, Weijun Lv, Na Han, Xiaozhao Fang, Jie Wen, Jiaxing Li, Guoxu Zhou
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 semantic-aware fusion (alpha) in membership learning (ablation) | PSCA · MNIST->USPS cross-domain retrieval | MAP (%) at 64 bits: 61.68 -> 87.35 | Improved |
| add semantic consistency alignment (geometry-vs-semantic weighting) (ablation) | PSCA · MNIST->USPS cross-domain retrieval | MAP (%) at 64 bits: 82.77 -> 87.35 | Improved |
| add orthogonal prototype learning (ablation) | PSCA · MNIST->USPS cross-domain retrieval | MAP (%) at 64 bits: 43.19 -> 87.35 | Improved |
| quantize reconstructed features instead of projected features (ablation) | PSCA · MNIST->USPS cross-domain retrieval | MAP (%) at 64 bits: 79.87 -> 87.35 | Improved |
| PSCA vs best baseline cross-domain | PSCA · Office-Home (six cases) | MAP (%): +8.82% average over second best | Improved |
| PSCA vs deep method CPH | PSCA · Office-Home 64 bits | MAP (%): +1.98% over CPH | Improved |
| PSCA vs best baseline single-domain | PSCA · Office-31 A->D single-domain | MAP (%): 59.54 vs 58.05 (SGHL) | No clear effect |
| PSCA vs COUPLE | PSCA · MNIST-USPS | MAP (%): +15.89% over COUPLE | Improved |
Closest papers by meaning
- Effective Comparative Prototype Hashing for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.90)
- Conformalized Hierarchical Calibration for Uncertainty-Aware Adaptive Hashing (ICLR 2026 · similarity 0.89)
- Collaborative Semantic Consistency Alignment for Blended-Target Domain Adaptation (AAAI 2025 · similarity 0.87)
- Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation (AAAI 2025 · similarity 0.86)
- Semantic Feature Learning for Universal Unsupervised Cross-Domain Retrieval (NeurIPS 2024 · similarity 0.86)
- RoDA: Robust Domain Alignment for Cross-Domain Retrieval Against Label Noise (AAAI 2025 · 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.
