Search Results - "Shang, Xinyi"

Greenland Ice Sheet Daily Surface Melt Flux Observed From Space by Zheng, Lei, Cheng, Xiao, Shang, Xinyi, Chen, Zhuoqi, Liang, Qi, Wang, Kang

“…Greenland Ice Sheet (GrIS) surface melt has contributed to the global sea‐level rise and the ongoing warming is expected to promote this process. This study…”
Get full text

Decadal Changes in Greenland Ice Sheet Firn Aquifers from Radar Scatterometer by Shang, Xinyi, Cheng, Xiao, Zheng, Lei, Liang, Qi, Chi, Zhaohui

“…Surface meltwater runoff is believed to be the main cause of the alarming mass loss in the Greenland Ice Sheet (GrIS); however, recent research has shown that…”
Get full text

An On-Orbit Relative Sensor Normalization for Unbalance Images from the Ice Pathfinder Satellite (BNU-1) by Zhang, Sishi, Shang, Xinyi, Li, Lanjing, Zhang, Ying, Wu, Xiaoxu, Hui, Fengming, Huang, Huabing, Cheng, Xiao

“…The Ice Pathfinder satellite (code: BNU-1) is the first Chinese microsatellite, designed for monitoring polar climate and environmental changes. The major…”
Get full text

GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost by Shang, Xinyi, Sun, Peng, Lin, Tao

“…Recent advancements in dataset distillation have demonstrated the significant benefits of employing soft labels generated by pre-trained teacher models. In…”
Get full text

No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier by Li, Zexi, Shang, Xinyi, He, Rui, Lin, Tao, Wu, Chao

“…Data heterogeneity is an inherent challenge that hinders the performance of federated learning (FL). Recent studies have identified the biased classifiers of…”
Get full text

Revisiting Weighted Aggregation in Federated Learning with Neural Networks by Li, Zexi, Lin, Tao, Shang, Xinyi, Wu, Chao

“…In federated learning (FL), weighted aggregation of local models is conducted to generate a global model, and the aggregation weights are normalized (the sum…”
Get full text

Personalized Federated Learning on Heterogeneous and Long-Tailed Data via Expert Collaborative Learning by Lv, Fengling, Shang, Xinyi, Zhou, Yang, Zhang, Yiqun, Li, Mengke, Lu, Yang

“…Personalized Federated Learning (PFL) aims to acquire customized models for each client without disclosing raw data by leveraging the collective knowledge of…”
Get full text

FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation by Shang, Xinyi, Lu, Yang, Cheung, Yiu-ming, Wang, Hanzi

“…Federated learning provides a privacy guarantee for generating good deep learning models on distributed clients with different kinds of data. Nevertheless,…”
Get full text

Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features by Shang, Xinyi, Lu, Yang, Huang, Gang, Wang, Hanzi

“…Federated learning (FL) provides a privacy-preserving solution for distributed machine learning tasks. One challenging problem that severely damages the…”
Get full text

Federated Semi-Supervised Learning with Annotation Heterogeneity by Shang, Xinyi, Huang, Gang, Lu, Yang, Lou, Jian, Han, Bo, Cheung, Yiu-ming, Wang, Hanzi

“…Federated Semi-Supervised Learning (FSSL) aims to learn a global model from different clients in an environment with both labeled and unlabeled data. Most of…”
Get full text

FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation by Shang, Xinyi, Lu, Yang, Cheung, Yiu-Ming, Wang, Hanzi

“…Federated learning provides a privacy guarantee for generating good deep learning models on distributed clients with different kinds of data. Nevertheless,…”
Get full text

Improved Model of Common Radix and Rhizome Chinese Herbal Medicine Classification Based VGG16 by Wang, Kunhui, Zhao, Yongtao, Wang, Yongzhe, Shang, Xinyi, Zhao, Wenjing, Cao, Zhong

“…Chinese Herbal Medicine (CHM) is a medicinal treasure of the Chinese nation, research on the identification and classification of CHM can help promote the…”
Get full text