Research map / Label-efficient and robust learning / Knowledge distillation
From Predictions to Embeddings: Dual Knowledge Distillation for Instance-Dependent Partial Label Learning
Lilong Duan, Ke Wang, Yao Zhang, Jun Tang
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 fine-grained semantic distillation (Lfd) (ablation) | DKDP · CIFAR-100 | accuracy: 68.05 -> 70.72 | Improved |
| add fine-grained semantic distillation (Lfd) (ablation) | DKDP · Flower-102 | accuracy: 44.36 -> 48.92 | Improved |
| add fine-grained semantic distillation (Lfd) (ablation) | DKDP · KMNIST | accuracy: 97.55 -> 98.49 | Improved |
| add fine-grained semantic distillation (Lfd) (ablation) | DKDP · CIFAR-10 | accuracy: 90.89 -> 93.64 | Improved |
| add constrained projection distillation (Lkd) (ablation) | DKDP w/o Lfd · CIFAR-10 | accuracy: 72.95 -> 90.89 | Improved |
| add constrained projection distillation (Lkd) (ablation) | DKDP w/o Lfd · FMNIST | accuracy: 78.85 -> 90.99 | Improved |
Closest papers by meaning
- Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning (AAAI 2024 · similarity 0.94)
- Partial Label Causal Representation Learning for Instance-Dependent Supervision and Domain Generalization (AAAI 2025 · similarity 0.89)
- Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency (ICML 2024 · similarity 0.89)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.89)
- Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning (NeurIPS 2025 · similarity 0.88)
- Disentangled Partial Label Learning (AAAI 2024 · similarity 0.88)
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.
