DIP-KD achieves state-of-the-art results in black-box data-free knowledge distillation across 12 benchmarks by synthesizing diverse image priors, applying contrastive learning, and using a primer student for soft-probability transfer.
Tiny imagenet visual recognition challenge.CS 231N, 2015
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
An adaptive high-confidence image selection scheme during GAN training expands diversity in the distillation set for black-box few-shot KD and yields SOTA student accuracy on seven image datasets.
citing papers explorer
-
Diverse Image Priors for Black-box Data-free Knowledge Distillation
DIP-KD achieves state-of-the-art results in black-box data-free knowledge distillation across 12 benchmarks by synthesizing diverse image priors, applying contrastive learning, and using a primer student for soft-probability transfer.
-
Improving Diversity in Black-box Few-shot Knowledge Distillation
An adaptive high-confidence image selection scheme during GAN training expands diversity in the distillation set for black-box few-shot KD and yields SOTA student accuracy on seven image datasets.