Výsledky vyhledávání - "Zhan, Xueying"

Report

AutoAL: Automated Active Learning with Differentiable Query Strategy Search

Autor: Wang, Yifeng, Zhan, Xueying, Huang, Siyu

As deep learning continues to evolve, the need for data efficiency becomes increasingly important. Considering labeling large datasets is both time-consuming and expensive, active learning (AL) provides a promising solution to this challenge by itera

Externí odkaz: http://arxiv.org/abs/2410.13853

Zobrazit plný text záznamu

Report

CryoMAE: Few-Shot Cryo-EM Particle Picking with Masked Autoencoders

Autor: Xu, Chentianye, Zhan, Xueying, Xu, Min

Cryo-electron microscopy (cryo-EM) emerges as a pivotal technology for determining the architecture of cells, viruses, and protein assemblies at near-atomic resolution. Traditional particle picking, a key step in cryo-EM, struggles with manual effort

Externí odkaz: http://arxiv.org/abs/2404.10178

Zobrazit plný text záznamu

Report

Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarios

Autor: Zhan, Xueying, Dai, Zeyu, Wang, Qingzhong, Li, Qing, Xiong, Haoyi, Dou, Dejing, Chan, Antoni B.

Pool-based Active Learning (AL) has achieved great success in minimizing labeling cost by sequentially selecting informative unlabeled samples from a large unlabeled data pool and querying their labels from oracle/annotators. However, existing AL sam

Externí odkaz: http://arxiv.org/abs/2207.01190

Zobrazit plný text záznamu

Report

Deep Active Learning with Noise Stability

Autor: Li, Xingjian, Yang, Pengkun, Gu, Yangcheng, Zhan, Xueying, Wang, Tianyang, Xu, Min, Xu, Chengzhong

Uncertainty estimation for unlabeled data is crucial to active learning. With a deep neural network employed as the backbone model, the data selection process is highly challenging due to the potential over-confidence of the model inference. Existing

Externí odkaz: http://arxiv.org/abs/2205.13340

Zobrazit plný text záznamu

Report

A Comparative Survey of Deep Active Learning

Autor: Zhan, Xueying, Wang, Qingzhong, Huang, Kuan-hao, Xiong, Haoyi, Dou, Dejing, Chan, Antoni B.

While deep learning (DL) is data-hungry and usually relies on extensive labeled data to deliver good performance, Active Learning (AL) reduces labeling costs by selecting a small proportion of samples from unlabeled data for labeling and training. Th

Externí odkaz: http://arxiv.org/abs/2203.13450

Zobrazit plný text záznamu

Report

Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processes

Autor: Zhan, Xueying, Li, Qing, Chan, Antoni B.

Active learning aims to achieve greater accuracy with less training data by selecting the most useful data samples from which it learns. Single-criterion based methods (i.e., informativeness and representativeness based methods) are simple and effici

Externí odkaz: http://arxiv.org/abs/2107.01622

Zobrazit plný text záznamu

Report

ALdataset: a benchmark for pool-based active learning

Autor: Zhan, Xueying, Chan, Antoni Bert

Active learning (AL) is a subfield of machine learning (ML) in which a learning algorithm could achieve good accuracy with less training samples by interactively querying a user/oracle to label new data points. Pool-based AL is well-motivated in many

Externí odkaz: http://arxiv.org/abs/2010.08161

Zobrazit plný text záznamu