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 …

Challenges, opportunities, and prospects of adopting and using smart digital technologies in learning environments: An iterative review

S Mhlongo, K Mbatha, B Ramatsetse, R Dlamini - Heliyon, 2023 - cell.com
The adoption of smart digital technologies in the education system has grown exponentially
over the years, creating new possibilities to improve teaching and enhance learning. Against …

Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels

L Jiang, Z Zhou, T Leung, LJ Li… - … conference on machine …, 2018 - proceedings.mlr.press
Recent deep networks are capable of memorizing the entire data even when the labels are
completely random. To overcome the overfitting on corrupted labels, we propose a novel …

Active bias: Training more accurate neural networks by emphasizing high variance samples

HS Chang, E Learned-Miller… - Advances in Neural …, 2017 - proceedings.neurips.cc
Self-paced learning and hard example mining re-weight training instances to improve
learning accuracy. This paper presents two improved alternatives based on lightweight …

Self-paced ARIMA for robust time series prediction

Y Li, K Wu, J Liu - Knowledge-Based Systems, 2023 - Elsevier
For time series prediction tasks, the autoregressive integrated moving average (ARIMA)
model is one of the most classical and popular linear models, and extended applications …

TSASNet: Tooth segmentation on dental panoramic X-ray images by Two-Stage Attention Segmentation Network

Y Zhao, P Li, C Gao, Y Liu, Q Chen, F Yang… - Knowledge-Based …, 2020 - Elsevier
Tooth segmentation acts as a crucial and fundamental role in dentistry for doctors to make
diagnosis and treatment plans. In this paper, we propose a Two-Stage Attention …

Leveraging prior-knowledge for weakly supervised object detection under a collaborative self-paced curriculum learning framework

D Zhang, J Han, L Zhao, D Meng - International Journal of Computer …, 2019 - Springer
Weakly supervised object detection is an interesting yet challenging research topic in
computer vision community, which aims at learning object models to localize and detect the …

SLNL: a novel method for gene selection and phenotype classification

HH Huang, NQ Wu, Y Liang… - International Journal of …, 2022 - Wiley Online Library
One of the central tasks of genome research is to predict phenotypes and discover some
important gene biomarkers. However, there are three main problems in analyzing genomics …

Few-example object detection with model communication

X Dong, L Zheng, F Ma, Y Yang… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
In this paper, we study object detection using a large pool of unlabeled images and only a
few labeled images per category, named “few-example object detection”. The key challenge …

Adaptive reverse graph learning for robust subspace learning

C Yuan, Z Zhong, C Lei, X Zhu, R Hu - Information Processing & …, 2021 - Elsevier
Subspace learning decreases the dimensions for high-dimensional data by projecting the
original data into a low-dimensional subspace, as well as preserving the similarity among …