Search Results for author: Peng Peng

Found 9 papers, 2 papers with code

SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II

no code implementations24 Dec 2020 Xiangjun Wang, Junxiao Song, Penghui Qi, Peng Peng, Zhenkun Tang, Wei zhang, Weimin Li, Xiongjun Pi, Jujie He, Chao GAO, Haitao Long, Quan Yuan

In this paper, we will share the key insights and optimizations on efficient imitation learning and reinforcement learning for StarCraft II full game.

Imitation Learning Starcraft +1

How to fine-tune deep neural networks in few-shot learning?

no code implementations1 Dec 2020 Peng Peng, Jiugen Wang

Fine-tuning of a deep model is simple and effective few-shot learning method.

Few-Shot Learning

A Unified Structure for Efficient RGB and RGB-D Salient Object Detection

no code implementations1 Dec 2020 Peng Peng, Yong-Jie Li

The proposed structure is simple yet effective; the rich context information of RGB and depth can be appropriately extracted and fused by the proposed structure efficiently.

RGB-D Salient Object Detection Salient Object Detection

Segmentation overlapping wear particles with few labelled data and imbalance sample

no code implementations20 Nov 2020 Peng Peng, Jiugen Wang

The region segmentation network is an improved U shape network, and it is applied to separate the wear debris form background of ferrograph image.

Edge Detection Semantic Segmentation

Ferrograph image classification

no code implementations14 Oct 2020 Peng Peng, Jiugen Wang

For the problem of insufficient samples, we first proposed a data augmentation algorithm based on the permutation of image patches.

Classification Data Augmentation +2

Continual Match Based Training in Pommerman: Technical Report

no code implementations18 Dec 2018 Peng Peng, Liang Pang, Yufeng Yuan, Chao GAO

We show in the experiments that Pommerman is a perfect environment for studying continual learning, and the agent can improve its performance by continually learning new skills without forgetting the old ones.

Continual Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.