Research map / Label-efficient and robust learning / Knowledge distillation
Zero-Shot Knowledge Distillation in Deep Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 Data Impression augmentation (ablation) | ZSKD · MNIST | accuracy: 96.98 -> 98.77 | Helped |
| add Data Impression augmentation (ablation) | ZSKD · Fashion MNIST | accuracy: 69.37 -> 79.62 | Helped |
| add Data Impression augmentation (ablation) | ZSKD · CIFAR-10 | accuracy: 56.80 -> 69.56 | Helped |
| use class similarity prior instead of a uniform prior (ablation) | ZSKD · MNIST | accuracy: 95.16 -> 96.98 | Helped |
| use class similarity prior instead of a uniform prior (ablation) | ZSKD · Fashion MNIST | accuracy: 56.24 -> 69.37 | Helped |
| use class similarity prior instead of a uniform prior (ablation) | ZSKD · CIFAR-10 | accuracy: 49.23 -> 56.80 | Helped |
| omit the student ground-truth cross-entropy term and use only distillation loss (ablation) | ZSKD · MNIST, Fashion MNIST, and CIFAR-10 | accuracy | No clear effect |
| increase the number of Data Impressions in the transfer set (ablation) | ZSKD · MNIST, Fashion MNIST, and CIFAR-10 | accuracy | Helped |
| use Data Impressions instead of Class Impressions (ablation) | zero-shot distillation · MNIST, Fashion MNIST, and CIFAR-10 | accuracy | Helped |
Closest papers by meaning
- Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model (ICML 2021 · similarity 0.90)
- Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy (ICLR 2018 · similarity 0.90)
- Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-training of Deep Networks (ICLR 2025 · similarity 0.88)
- VkD: Improving Knowledge Distillation using Orthogonal Projections (CVPR 2024 · similarity 0.87)
- Small Scale Data-Free Knowledge Distillation (CVPR 2024 · similarity 0.86)
- DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer (NeurIPS 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.