60 citations · 103 across the 12 of their papers we have counts for
12 papers
POP: Prompt Of Prompts for Continual Learning
Zhiyuan Hu, Jiancheng Lyu, Dashan Gao +1
Continual learning (CL) has attracted increasing attention in the recent past. It aims to mimic the human ability to learn new concepts without catastrophic forgetting. While exist…
Dense Network Expansion for Class Incremental Learning
Zhiyuan Hu, Yunsheng Li, Jiancheng Lyu +2
The problem of class incremental learning (CIL) is considered. State-of-the-art approaches use a dynamic architecture based on network expansion (NE), in which a task expert is add…
MobileInst: Video Instance Segmentation on the Mobile
Renhong Zhang, Tianheng Cheng, Shusheng Yang +8
Video instance segmentation on mobile devices is an important yet very challenging edge AI problem. It mainly suffers from (1) heavy computation and memory costs for frame-by-frame…
Computing Residual Diffusivity by Adaptive Basis Learning via Super-Resolution Deep Neural Networks
Jiancheng Lyu, Jack Xin, Yifeng Yu
It is expensive to compute residual diffusivity in chaotic in-compressible flows by solving advection-diffusion equation due to the formation of sharp internal layers in the advect…
A Channel-Pruned and Weight-Binarized Convolutional Neural Network for Keyword Spotting
Jiancheng Lyu, Spencer Sheen
We study channel number reduction in combination with weight binarization (1-bit weight precision) to trim a convolutional neural network for a keyword spotting (classification) ta…
Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets
Penghang Yin, Jiancheng Lyu, Shuai Zhang +3
Training activation quantized neural networks involves minimizing a piecewise constant function whose gradient vanishes almost everywhere, which is undesirable for the standard bac…