Research map / Label-efficient and robust learning / Domain adaptation and generalization
Generalized Domain Conditioned Adaptation Network
Shuang Li, Binhui Xie, Qiuxia Lin, Chi Harold Liu, Gao Ming Huang, Guoren 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 GDCAN adaptive attention module (vs w/o AAM) (ablation) | GDCAN · Office-Home | average accuracy: 69.2 -> 71.5 | Improved |
| add first feature adaptation module with regularization (ablation) | GDCAN · Office-Home | average accuracy: 66.7 -> 71.5 | Improved |
| add second feature adaptation module with regularization (ablation) | GDCAN · Office-Home | average accuracy: 68.3 -> 71.5 | Improved |
| add feature alignment modules (all) (ablation) | GDCAN · Office-Home | average accuracy: 59.0 -> 71.5 | Improved |
| add regularization loss at first module (ablation) | GDCAN · Office-Home | average accuracy: 68.8 -> 71.5 | Improved |
| add regularization loss at second module (ablation) | GDCAN · Office-Home | average accuracy: 70.4 -> 71.5 | Improved |
| add target entropy loss (ablation) | GDCAN · Office-Home | average accuracy: 70.7 -> 71.5 | Improved |
| make channel attention adaptive (GDCAN over DCAN) | GDCAN · DomainNet ResNet-101 | average accuracy: 32.4 -> 34.7 | Improved |
| make channel attention adaptive (GDCAN over DCAN) | GDCAN · DomainNet ResNet-50 | average accuracy: 29.2 -> 32.2 | Improved |
| make channel attention adaptive (GDCAN over DCAN) | GDCAN · Office-31 | average accuracy: 89.5 -> 89.7 | No clear effect |
| make channel attention adaptive (GDCAN over DCAN) | GDCAN · ImageCLEF-DA | average accuracy: 88.3 -> 88.7 | No clear effect |
| plug DCAN / GDCAN into CDAN | CDAN · Office-Home | average accuracy: 63.8 -> 69.6 -> 70.3 | Improved |
Closest papers by meaning
- Domain Conditioned Adaptation Network (AAAI 2020 · similarity 0.97)
- Transferable Representation Learning with Deep Adaptation Networks (TPAMI 2018 · similarity 0.91)
- Learning Across Tasks for Zero-Shot Domain Adaptation From a Single Source Domain (TPAMI 2021 · similarity 0.90)
- Heuristic Domain Adaptation (NeurIPS 2020 · similarity 0.90)
- A Broad Study of Pre-training for Domain Generalization and Adaptation (ECCV 2022 · similarity 0.90)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.89)
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.
