Research map / Architectures and efficiency / CNN design
A Dictionary Approach to Domain-Invariant Learning in Deep Networks
Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu
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 DAFD to DANN | DANN · Digits S->M | accuracy (%): 73.9 -> 82.1 | Improved |
| add DAFD to ADDA | ADDA · Digits average | accuracy (%): 85.1 -> 89.7 | Improved |
| add DAFD to CDAN+E | CDAN+E · Digits average | accuracy (%): 94.3 -> 97.4 | Improved |
| add DAFD to DANN | DANN (AlexNet) · Office-31 average | accuracy (%): 74.3 -> 75.8 | Improved |
| add DAFD to ADDA | ADDA (AlexNet) · Office-31 average | accuracy (%): 74.7 -> 76.7 | Improved |
| add DAFD to DANN | DANN (ResNet) · Office-31 average | accuracy (%): 82.2 -> 84.35 | Improved |
| add DAFD to ADDA | ADDA (ResNet) · Office-31 average | accuracy (%): 82.9 -> 83.9 | Improved |
| add DAFD to CDAN+E | CDAN+E (ResNet) · Office-31 average | accuracy (%): 87.7 -> 89.3 | Improved |
| add DAFD to AdaptSegNet | AdaptSegNet (ResNet) · GTA->Cityscapes | IoU: 42.4 -> 45.0 | Improved |
| add DAFD to AdaptSegNet | AdaptSegNet (VGG) · GTA->Cityscapes | IoU: 35.0 -> 36.4 | Improved |
| add DAFD to FCNs in the wild | FCN WLD (VGG) · GTA->Cityscapes | IoU: 27.1 -> 32.7 | Improved |
| replace per-domain full filters by DAFD atoms | VGG-16 per extra domain · VGG-16 | additional parameters (M): 14.71M -> 0.0007M | Improved |
Closest papers by meaning
- Domain Conditioned Adaptation Network (AAAI 2020 · similarity 0.89)
- Domain Adaptation with Invariant Representation Learning: What Transformations to Learn? (NeurIPS 2021 · similarity 0.89)
- On Learning Invariant Representations for Domain Adaptation (ICML 2019 · similarity 0.88)
- Beyond Sharing Weights for Deep Domain Adaptation (TPAMI 2018 · similarity 0.88)
- Enhancing Domain Adaptation through Prompt Gradient Alignment (NeurIPS 2024 · similarity 0.87)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · 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.
