Search Results for author:
Found 8 papers, 7 papers with code
Data Generation for Hardware-Friendly Post-Training Quantization
We analyze existing data generation methods based on batch normalization (BN) matching and identify several gaps between synthetic and real data: 1) Current generation algorithms do not optimize the entire synthetic dataset simultaneously; 2) Data augmentations applied during training are often overlooked; and 3) A distribution shift occurs in the final model layers due to the absence of BN in those layers.
EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization
In addition, we leverage the Hessian upper bound to improve the weight quantization parameters selection by focusing on the more sensitive elements in the weight tensors.
Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain Adaptation
We propose to reconcile this conflict by aligning the entropy minimization objective with that of the pseudo labels' cross entropy.
Learning to Bound: A Generative Cramér-Rao Bound
The Cram\'er-Rao bound (CRB), a well-known lower bound on the performance of any unbiased parameter estimator, has been used to study a wide variety of problems.
HPTQ: Hardware-Friendly Post Training Quantization
Neural network quantization enables the deployment of models on edge devices.
Ranked #1 on
Quantization
on MS COCO
Multi-View Image-to-Image Translation Supervised by 3D Pose
Experimental results on the CMU-Panoptic dataset demonstrate the effectiveness of the suggested framework in generating photo-realistic images of persons with new poses that are more consistent across all views in comparison to a standard Image-to-Image baseline.
HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs
In this work, we introduce the Hardware Friendly Mixed Precision Quantization Block (HMQ) in order to meet this requirement.
Ranked #13 on
Quantization
on ImageNet
Genetic Network Architecture Search
We propose a method for learning the neural network architecture that based on Genetic Algorithm (GA).
