Zhengyang Zhuge — accepted AI-conference papers

2024

Patch-Aware Sample Selection for Efficient Masked Image Modeling

Zhengyang Zhuge, Jiaxing Wang, Yong Li, Yongjun Bao, Peisong Wang, Jian Cheng

AAAI 2024technical

Nowadays sample selection is drawing increasing attention. By extracting and training only on the most informative subset, sample selection can effectively reduce the training cost. Although sample selection is effective in conventional supervised learning, applying it to Masked Image Modeling (MIM)…

Cited by 4 Source ↗PDF ↗Scholar ↗

2024

Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration

Zhengyang Zhuge, Peisong Wang, Xingting Yao, Jian Cheng

ICML 2024poster

Nowadays Spiking Transformers have exhibited remarkable performance close to Artificial Neural Networks (ANNs), while enjoying the inherent energy-efficiency of Spiking Neural Networks (SNNs). However, training Spiking Transformers on GPUs is considerably more time-consuming compared to the ANN coun…

Cited by 0 Source ↗PDF ↗Scholar ↗