Proposes EmaQ and EmaQ-LT methods for multi-domain and long-tailed DNN quantization with CDF alignment, sensitivity aggregation, class-conditioned scaling, and convergence guarantees, showing strong low-bit results on Office-31, Digits, and long-tailed CIFAR variants.
Gaqat: gradient-adaptive quantization-aware training for domain gen- eralization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Toward Multi-Domain and Long-Tailed Quantization via Feature Alignment and Scaling
Proposes EmaQ and EmaQ-LT methods for multi-domain and long-tailed DNN quantization with CDF alignment, sensitivity aggregation, class-conditioned scaling, and convergence guarantees, showing strong low-bit results on Office-31, Digits, and long-tailed CIFAR variants.