New C2R Framework Enhances Robustness in Dataset Distillation

Researchers have developed a new framework called Contrastive Curriculum for Robust Dataset Distillation (C$^2$R) to improve the robustness of distilled datasets. Unlike previous methods that treated all adversarial perturbations equally, C$^2$R prioritizes samples with the smallest robust margins and explicitly widens the separation between decision boundaries. This approach leads to better accuracy-robustness trade-offs, achieving superior robust accuracy across various datasets and attacks. AI

RANK_REASON The cluster contains a research paper detailing a new framework for dataset distillation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• C$^2$R
• CIFAR-10
• CIFAR-100
• Contrastive Curriculum for Robust Dataset Distillation
• ImageNet-1K
• Muquan Li
• Tiny-ImageNet

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →