Research map / Label-efficient and robust learning / Domain adaptation and generalization
HGNet: Hybrid Generative Network for Zero-shot Domain Adaptation
Haifeng Xia, Zhengming Ding
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 hybrid reconstruction (ablation) | HGNet · N to G: Fashion-MNIST (IRT MNIST) | accuracy (%): 10% | Improved |
| increase feature alignment weight lambda from 0.1 to 15 (ablation) | HGNet · N to G adaptation | accuracy (%): 0.1 -> 15 | Improved |
| use HGNet instead of CoCoGAN (feature separation, no target generation) | HGNet · G to C: Fashion-MNIST (IRT MNIST) | accuracy (%): 56.8 -> 64.5 | Improved |
| use HGNet instead of CoCoGAN | HGNet · G to N: EMNIST (IRT Fashion-MNIST) | accuracy (%): 56.5 -> 62.3 | Improved |
| use HGNet instead of CoCoGAN | HGNet · G to E: EMNIST (IRT MNIST) | accuracy (%): 77.9 -> 81.1 | Improved |
| use HGNet instead of CoCoGAN | HGNet · G to C: EMNIST (IRT MNIST) | accuracy (%): 75.0 -> 71.3 | Hurt |
| use HGNet instead of CoCoGAN | HGNet · C to G: Fashion-MNIST (IRT EMNIST) | accuracy (%): 70.2 -> 68.5 | Hurt |
Closest papers by meaning
- Collaborative Learning With Disentangled Features for Zero-Shot Domain Adaptation (ICCV 2021 · similarity 0.89)
- Learning Across Tasks for Zero-Shot Domain Adaptation From a Single Source Domain (TPAMI 2021 · similarity 0.89)
- Adversarial Learning for Zero-shot Domain Adaptation (ECCV 2020 · similarity 0.89)
- Unified Language-driven Zero-shot Domain Adaptation (CVPR 2024 · similarity 0.88)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.87)
- Few-shot Hybrid Domain Adaptation of Image Generator (ICLR 2024 · similarity 0.87)
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.
