← Search

Yuxian Qiu

2 accepted papers

2022

SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation

ICLR 2022poster

Quantization of deep neural networks (DNN) has been proven effective for compressing and accelerating DNN models. Data-free quantization (DFQ) is a promising approach without the original datasets under privacy-sensitive and confidential scenarios. However, current DFQ solutions degrade accuracy, ne…

2019

Adversarial Defense Through Network Profiling Based Path Extraction

CVPR 2019poster

Recently, researchers have started decomposing deep neural network models according to their semantics or functions. Recent work has shown the effectiveness of decomposed functional blocks for defending adversarial attacks, which add small input perturbation to the input image to fool the DNN models…

Cited by 65PDFScholar