← Search

Tuanhui Li

2 accepted papers

2020

Sparse Adversarial Attack via Perturbation Factorization

ECCV 2020poster

This work studies the sparse adversarial attack, which aims to generate adversarial perturbations onto partial positions of one benign image, such that the perturbed image is incorrectly predicted by one deep neural network (DNN) model. The sparse adversarial attack involves two challenges, i.e., wh…

2019

Compressing Convolutional Neural Networks via Factorized Convolutional Filters

CVPR 2019poster

This work studies the model compression for deep convolutional neural networks (CNNs) via filter pruning. The workflow of a traditional pruning consists of three sequential stages: pre-training the original model, selecting the pre-trained filters via ranking according to a manually designed criteri…

Cited by 133PDFcodeScholar