Yuhao Zhu

Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity

2020

Network pruning can reduce the high computation cost of deep neural network (DNN) models. However, to maintain their accuracies, sparse models often carry randomly-distributed weights, leading to irregular computations. Consequently, sparse models cannot achieve meaningful …

Multiscale Dynamic Graph Representation for Biometric Recognition with Occlusions

2023 · arXiv (Cornell University)

Occlusion is a common problem with biometric recognition in the wild. The generalization ability of CNNs greatly decreases due to the adverse effects of various occlusions. To this end, we propose a novel unified framework …