2.7k citations
- Chinese University of Hong KongHK90 papers
- University of Hong KongHK89 papers
- Sun Yat-sen UniversityCN81 papers
- Chinese Academy of SciencesCN75 papers
- University of Science and Technology of ChinaCN63 papers
- Tsinghua UniversityCN51 papers
- Beijing Normal UniversityCN45 papers
- Shenzhen Technology UniversityCN44 papers
- Shanghai Jiao Tong UniversityCN42 papers
- Xi'an Jiaotong UniversityCN42 papers
- National University of Defense TechnologyCN40 papers
- China Institute of Atomic EnergyCN39 papers
5 papers · 2 filters
A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications
Xinlei Zhou, Han Liu, Farhad Pourpanah +2
Quantifying the uncertainty of supervised learning models plays an important role in making more reliable predictions. Epistemic uncertainty, which usually is due to insufficient k…
Clustering-Based Representation Learning through Output Translation and Its Application to Remote--Sensing Images
Qinglin Li, Bin Li, Jonathan M Garibaldi +1
In supervised deep learning, learning good representations for remote--sensing images (RSI) relies on manual annotations. However, in the area of remote sensing, it is hard to obta…
Reproducibility Companion Paper: Knowledge Enhanced Neural Fashion Trend Forecasting
Yunshan Ma, Yujuan Ding, Xun Yang +5
This companion paper supports the replication of the fashion trend forecasting experiments with the KERN (Knowledge Enhanced Recurrent Network) method that we presented in the ICMR…
Slashing Communication Traffic in Federated Learning by Transmitting Clustered Model Updates
Laizhong Cui, Xiaoxin Su, Yipeng Zhou +1
Federated Learning (FL) is an emerging decentralized learning framework through which multiple clients can collaboratively train a learning model. However, a major obstacle that im…
Adversarial Learning with Cost-Sensitive Classes
Haojing Shen, Sihong Chen, Ran Wang +1
It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining c…