Research map / Label-efficient and robust learning / Domain adaptation and generalization
Heterogeneous Transfer Learning via Deep Matrix Completion with Adversarial Kernel Embedding
Haoliang Li, Sinno Jialin Pan, Renjie Wan, Alex C. Kot
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 low-rank constraint (ablation) | Deep-MCA · Object recognition A/A | accuracy (%): 43.7 -> 47.4 | Improved |
| add low-rank constraint (ablation) | Deep-MCA · Object recognition C/C | accuracy (%): 30.2 -> 34.7 | Improved |
| add low-rank constraint (ablation) | Deep-MCA · Object recognition W/W | accuracy (%): 62.3 -> 66.4 | Improved |
| add injective regularization (ablation) | Deep-MCA · Object recognition A/A | accuracy (%): 47.0 -> 47.4 | No clear effect |
| add injective regularization (ablation) | Deep-MCA · Object recognition C/C | accuracy (%): 34.5 -> 34.7 | No clear effect |
| add injective regularization (ablation) | Deep-MCA · Object recognition W/W | accuracy (%): 63.1 -> 66.4 | Improved |
| add MMD regularization (ablation) | Deep-MCA · Object recognition A/A | accuracy (%): 43.0 -> 47.4 | Improved |
| add MMD regularization (ablation) | Deep-MCA · Object recognition C/C | accuracy (%): 32.0 -> 34.7 | Improved |
| add MMD regularization (ablation) | Deep-MCA · Object recognition W/W | accuracy (%): 58.4 -> 66.4 | Improved |
| add manifold regularization (ablation) | Deep-MCA · Object recognition A/A | accuracy (%): 44.6 -> 47.4 | Improved |
| add manifold regularization (ablation) | Deep-MCA · Object recognition C/C | accuracy (%): 30.4 -> 34.7 | Improved |
| add manifold regularization (ablation) | Deep-MCA · Object recognition W/W | accuracy (%): 62.7 -> 66.4 | Improved |
Closest papers by meaning
- Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning (NeurIPS 2018 · similarity 0.83)
- Improving the Adversarial Transferability of Vision Transformers with Virtual Dense Connection (AAAI 2024 · similarity 0.83)
- Heterogeneous Complementary Distillation (AAAI 2026 · similarity 0.83)
- Enhancing Representations Through Heterogeneous Self-Supervised Learning (TPAMI 2025 · similarity 0.83)
- Hypothesis Transfer Learning via Transformation Functions (NeurIPS 2017 · similarity 0.83)
- Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement (CVPR 2025 · similarity 0.82)
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.
