SOTAVerified

Data Free Quantization

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 37 papers

TitleStatusHype
Generative Low-bitwidth Data Free QuantizationCode1
Diverse Sample Generation: Pushing the Limit of Generative Data-free QuantizationCode1
It's All In the Teacher: Zero-Shot Quantization Brought Closer to the TeacherCode1
Towards Accurate Post-training Quantization for Diffusion ModelsCode1
Robustness-Guided Image Synthesis for Data-Free Quantization—0
Semantics Prompting Data-Free Quantization for Low-Bit Vision Transformers—0
SPIQ: Data-Free Per-Channel Static Input Quantization—0
Zero-Shot Learning of a Conditional Generative Adversarial Network for Data-Free Network Quantization—0
A method of using RSVD in residual calculation of LowBit GEMM—0
Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization—0
Show:102550
← PrevPage 2 of 4Next →

No leaderboard results yet.