4 papers
InWaveSR: Topography-Aware Super-Resolution Network for Internal Solitary Waves
Xinjie Wang, Zhongrui Li, Peng Han +4
The effective utilization of observational data is frequently hindered by insufficient resolution. To address this problem, we present a new spatio-temporal super-resolution (STSR)…
LoDisc: Learning Global-Local Discriminative Features for Self-Supervised Fine-Grained Visual Recognition
Jialu Shi, Zhiqiang Wei, Jie Nie +1
The self-supervised contrastive learning strategy has attracted considerable attention due to its exceptional ability in representation learning. However, current contrastive learn…
LR-CNN: Lightweight Row-centric Convolutional Neural Network Training for Memory Reduction
Zhigang Wang, Hangyu Yang, Ning Wang +5
In the last decade, Convolutional Neural Network with a multi-layer architecture has advanced rapidly. However, training its complex network is very space-consuming, since a lot of…
Accelerating Heterogeneous Tensor Parallelism via Flexible Workload Control
Zhigang Wang, Xu Zhang, Ning Wang +5
Transformer-based models are becoming deeper and larger recently. For better scalability, an underlying training solution in industry is to split billions of parameters (tensors) i…