AstroNet: When Astrocyte Meets Artificial Neural Network

no code implementations • CVPR 2023 • Mengqiao Han, Liyuan Pan, Xiabi Liu

Then, with the astrocytes, we propose an AstroNet that can adaptively optimize neuron connections and therefore achieves structure learning to achieve higher accuracy and efficiency.

RL-CoSeg : A Novel Image Co-Segmentation Algorithm with Deep Reinforcement Learning

no code implementations • 12 Apr 2022 • Xin Duan, Xiabi Liu, Xiaopeng Gong, Mengqiao Han

For the image co-segmentation problem, we propose a collaborative RL algorithm based on the A3C model.

reinforcement-learning Reinforcement Learning (RL) +1

Mining the Weights Knowledge for Optimizing Neural Network Structures

no code implementations • 11 Oct 2021 • Mengqiao Han, Xiabi Liu, Zhaoyang Hai, Xin Duan

We introduce a switcher neural network (SNN) that uses as inputs the weights of a task-specific neural network (called TNN for short).

Explore the Knowledge contained in Network Weights to Obtain Sparse Neural Networks

no code implementations • 26 Mar 2021 • Mengqiao Han, Xiabi Liu, Zhaoyang Hai, Zhengwen Li

We design a switcher neural network (SNN) to optimize the structure of the task neural network (TNN).

Image Classification