A survey on curriculum learning

X Wang, Y Chen, W Zhu - IEEE transactions on pattern analysis …, 2021‏ - ieeexplore.ieee.org
Curriculum learning (CL) is a training strategy that trains a machine learning model from
easier data to harder data, which imitates the meaningful learning order in human curricula …

A survey on deep active learning: Recent advances and new frontiers

D Li, Z Wang, Y Chen, R Jiang, W Ding… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Active learning seeks to achieve strong performance with fewer training samples. It does this
by iteratively asking an oracle to label newly selected samples in a human-in-the-loop …

Curriculum learning: A survey

P Soviany, RT Ionescu, P Rota, N Sebe - International Journal of …, 2022‏ - Springer
Training machine learning models in a meaningful order, from the easy samples to the hard
ones, using curriculum learning can provide performance improvements over the standard …

Multiple instance active learning for object detection

T Yuan, F Wan, M Fu, J Liu, S Xu… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Despite the substantial progress of active learning for image recognition, there still lacks an
instance-level active learning method specified for object detection. In this paper, we …

[PDF][PDF] A Comparative Survey: Benchmarking for Pool-based Active Learning.

X Zhan, H Liu, Q Li, AB Chan - IJCAI, 2021‏ - ijcai.org
Active learning (AL) is a subfield of machine learning (ML) in which a learning algorithm
aims to achieve good accuracy with fewer training samples by interactively querying the …

Active learning and bayesian optimization: A unified perspective to learn with a goal

F Di Fiore, M Nardelli, L Mainini - Archives of Computational Methods in …, 2024‏ - Springer
Science and Engineering applications are typically associated with expensive optimization
problem to identify optimal design solutions and states of the system of interest. Bayesian …

Similarity-based active learning methods

Q Sui, SK Ghosh - Expert Systems with Applications, 2024‏ - Elsevier
Active Learning has been a popular method to circumvent the labeling cost in machine
learning methods. The majority of active learning approaches can be classified into two …

Contrastive coding for active learning under class distribution mismatch

P Du, S Zhao, H Chen, S Chai… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Active learning (AL) is successful based on the assumption that labeled and unlabeled data
are obtained from the same class distribution. However, its performance deteriorates under …

Symmetric self-paced learning for domain generalization

D Zhao, YS Koh, G Dobbie, H Hu… - Proceedings of the AAAI …, 2024‏ - ojs.aaai.org
Deep learning methods often suffer performance degradation due to domain shift, where
discrepancies exist between training and testing data distributions. Domain generalization …

Exploring diversity-based active learning for 3d object detection in autonomous driving

J Lin, Z Liang, S Deng, L Cai, T Jiang… - IEEE Transactions …, 2024‏ - ieeexplore.ieee.org
3D object detection has recently received much attention due to its great potential in
autonomous vehicle (AV). The success of deep learning based object detectors relies on the …