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 21–30 of 37 papers

TitleStatusHype
Zero-Shot Learning of a Conditional Generative Adversarial Network for Data-Free Network Quantization—0
PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision TransformersCode1
Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization—0
Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization—0
It's All In the Teacher: Zero-Shot Quantization Brought Closer to the TeacherCode1
SPIQ: Data-Free Per-Channel Static Input Quantization—0
Patch Similarity Aware Data-Free Quantization for Vision TransformersCode1
SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian ApproximationCode1
Qimera: Data-free Quantization with Synthetic Boundary Supporting SamplesCode1
Diverse Sample Generation: Pushing the Limit of Generative Data-free QuantizationCode1
Show:102550
← PrevPage 3 of 4Next →

No leaderboard results yet.