Search Results for author: Fan Feng

Found 12 papers, 2 papers with code

A Benchmark and Empirical Analysis for Replay Strategies in Continual Learning

no code implementations4 Aug 2022 Qihan Yang, Fan Feng, Rosa Chan

Finally, a practical solution for selecting replay methods for various data distributions is provided.

Continual Learning

Factored Adaptation for Non-Stationary Reinforcement Learning

no code implementations30 Mar 2022 Fan Feng, Biwei Huang, Kun Zhang, Sara Magliacane

Dealing with non-stationarity in environments (e. g., in the transition dynamics) and objectives (e. g., in the reward functions) is a challenging problem that is crucial in real-world applications of reinforcement learning (RL).

reinforcement-learning

AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning

1 code implementation ICLR 2022 Biwei Huang, Fan Feng, Chaochao Lu, Sara Magliacane, Kun Zhang

We show that by explicitly leveraging this compact representation to encode changes, we can efficiently adapt the policy to the target domain, in which only a few samples are needed and further policy optimization is avoided.

Atari Games reinforcement-learning +1

Serial-EMD: Fast Empirical Mode Decomposition Method for Multi-dimensional Signals Based on Serialization

no code implementations22 Jun 2021 Jin Zhang, Fan Feng, Pere Marti-Puig, Cesar F. Caiafa, Zhe Sun, Feng Duan, Jordi Solé-Casals

Empirical mode decomposition (EMD) has developed into a prominent tool for adaptive, scale-based signal analysis in various fields like robotics, security and biomedical engineering.

Time Series

Improving Conversational Recommendation System by Pretraining on Billions Scale of Knowledge Graph

no code implementations30 Apr 2021 Chi-Man Wong, Fan Feng, Wen Zhang, Chi-Man Vong, Hui Chen, Yichi Zhang, Peng He, Huan Chen, Kun Zhao, Huajun Chen

We first construct a billion-scale conversation knowledge graph (CKG) from information about users, items and conversations, and then pretrain CKG by introducing knowledge graph embedding method and graph convolution network to encode semantic and structural information respectively. To make the CTR prediction model sensible of current state of users and the relationship between dialogues and items, we introduce user-state and dialogue-interaction representations based on pre-trained CKG and propose K-DCN. In K-DCN, we fuse the user-state representation, dialogue-interaction representation and other normal feature representations via deep cross network, which will give the rank of candidate items to be recommended. We experimentally prove that our proposal significantly outperforms baselines and show it's real application in Alime.

Click-Through Rate Prediction Knowledge Graph Embedding +1

Interfacial metric mechanics: stitching patterns of shape change in active sheets

no code implementations9 Feb 2021 Fan Feng, Daniel Duffy, John S. Biggins, Mark Warner

In contraction/elongation systems such as LCEs, we find an infinite set of compatible interfaces between any pair of patterns along which the metric is discontinuous, and a finite number across which the metric is continuous.

Soft Condensed Matter

OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learning

2 code implementations15 Nov 2019 Qi She, Fan Feng, Xinyue Hao, Qihan Yang, Chuanlin Lan, Vincenzo Lomonaco, Xuesong Shi, Zhengwei Wang, Yao Guo, Yimin Zhang, Fei Qiao, Rosa H. M. Chan

Yet, robotic vision poses unique challenges for applying visual algorithms developed from these standard computer vision datasets due to their implicit assumption over non-varying distributions for a fixed set of tasks.

Object Recognition

Deep joint rain and haze removal from single images

no code implementations21 Jan 2018 Liang Shen, Zihan Yue, Quan Chen, Fan Feng, Jie Ma

On the other hand, the accumulation of rain streaks from long distance makes the rain image look like haze veil.

Rain Removal

MSR-net:Low-light Image Enhancement Using Deep Convolutional Network

no code implementations7 Nov 2017 Liang Shen, Zihan Yue, Fan Feng, Quan Chen, Shihao Liu, Jie Ma

In this paper, a low-light image enhancement model based on convolutional neural network and Retinex theory is proposed.

Low-Light Image Enhancement

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