Data Free Quantization
14 papers with code • 2 benchmarks • 1 datasets
Data Free Quantization is a technique to achieve a highly accurate quantized model without accessing any training data.
Source: Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples
Libraries
Use these libraries to find Data Free Quantization models and implementationsMost implemented papers
Rethinking Data-Free Quantization as a Zero-Sum Game
how to generate the samples with desirable adaptability to benefit the quantized network?
Adaptive Data-Free Quantization
Data-free quantization (DFQ) recovers the performance of quantized network (Q) without the original data, but generates the fake sample via a generator (G) by learning from full-precision network (P), which, however, is totally independent of Q, overlooking the adaptability of the knowledge from generated samples, i. e., informative or not to the learning process of Q, resulting into the overflow of generalization error.
Towards Accurate Post-training Quantization for Diffusion Models
On the contrary, we design group-wise quantization functions for activation discretization in different timesteps and sample the optimal timestep for informative calibration image generation, so that our quantized diffusion model can reduce the discretization errors with negligible computational overhead.
Causal-DFQ: Causality Guided Data-free Network Quantization
Inspired by the causal understanding, we propose the Causality-guided Data-free Network Quantization method, Causal-DFQ, to eliminate the reliance on data via approaching an equilibrium of causality-driven intervened distributions.