Research map / Label-efficient and robust learning / Domain adaptation and generalization
Implicit Semantic Response Alignment for Partial Domain Adaptation
Read the paperCheck 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 implicit semantic response alignment | BA3US · Office-Home average | accuracy: 75.98 -> 78.20 | Helped |
| add implicit semantic response alignment | BA3US · Office31 average | accuracy: 97.80 -> 98.15 | Helped |
| add implicit semantic response alignment | BA3US · ImageNet-Caltech average | accuracy: 83.68 -> 84.50 | Helped |
| add implicit semantic response alignment | BA3US · ImageNet-Caltech I→C | accuracy: 84.00 -> 85.28 | Helped |
| add implicit semantic response alignment | SHOT · Office-Home | accuracy | No clear effect |
| add implicit semantic response alignment | A2TK · Office-Home | accuracy: 3% | Helped |
| add implicit semantic response alignment | BA3US · Office-Home Ar→Cl class Computer | per-class accuracy: 12.12 -> 59.60 | Helped |
| add implicit semantic response alignment | BA3US · Office-Home Ar→Cl class Clipboards | per-class accuracy: 67.50 -> 87.50 | Helped |
| add implicit semantic response alignment | BA3US · Office-Home Ar→Cl class Candles | per-class accuracy: 79.80 -> 70.71 | Hurt |
| add implicit semantic response alignment | BA3US · Office-Home Ar→Cl class Eraser | per-class accuracy: 0.00 -> 0.00 | No clear effect |
| increase ratio between alpha and beta loss weights (ablation) | Ours + BA3US · Office31 A→D, D→A | accuracy | Hurt |
| increase number of implicit topics (ablation) | Ours + BA3US · Office31 A→W, W→A | accuracy | Mixed |
Closest papers by meaning
- Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport (ICML 2025 · similarity 0.88)
- Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.88)
- Collaborative Semantic Consistency Alignment for Blended-Target Domain Adaptation (AAAI 2025 · similarity 0.87)
- Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm (AAAI 2025 · similarity 0.87)
- Balanced Learning for Domain Adaptive Semantic Segmentation (ICML 2025 · similarity 0.87)
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias (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.