MUSE generates multi-resolution, CAM-guided synthetic images for data-free knowledge distillation and reports two-digit accuracy gains over prior methods on ImageNet and smaller subsets.
Data-free network quantization with adversarial knowl- edge distillation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation
MUSE generates multi-resolution, CAM-guided synthetic images for data-free knowledge distillation and reports two-digit accuracy gains over prior methods on ImageNet and smaller subsets.