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 26–37 of 37 papers

TitleStatusHype
QNNRepair: Quantized Neural Network Repair—0
Rethinking Data-Free Quantization as a Zero-Sum GameCode0
ACQ: Improving Generative Data-free Quantization Via Attention Correction—0
Genie: Show Me the Data for QuantizationCode0
Zero-Shot Learning of a Conditional Generative Adversarial Network for Data-Free Network Quantization—0
Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization—0
Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization—0
SPIQ: Data-Free Per-Channel Static Input Quantization—0
Zero-shot Adversarial Quantization—0
Diversifying Sample Generation for Accurate Data-Free Quantization—0
Generative Zero-shot Network Quantization—0
Towards Accurate Quantization and Pruning via Data-free Knowledge Transfer—0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.