A survey on curriculum learning
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 …
easier data to harder data, which imitates the meaningful learning order in human curricula …
Curriculum learning: A survey
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 …
ones, using curriculum learning can provide performance improvements over the standard …
Suppressing uncertainties for large-scale facial expression recognition
Annotating a qualitative large-scale facial expression dataset is extremely difficult due to the
uncertainties caused by ambiguous facial expressions, low-quality facial images, and the …
uncertainties caused by ambiguous facial expressions, low-quality facial images, and the …
Multi-similarity loss with general pair weighting for deep metric learning
A family of loss functions built on pair-based computation have been proposed in the
literature which provide a myriad of solutions for deep metric learning. In this pa-per, we …
literature which provide a myriad of solutions for deep metric learning. In this pa-per, we …
Meta-weight-net: Learning an explicit mapping for sample weighting
Current deep neural networks (DNNs) can easily overfit to biased training data with
corrupted labels or class imbalance. Sample re-weighting strategy is commonly used to …
corrupted labels or class imbalance. Sample re-weighting strategy is commonly used to …
Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels
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 …
completely random. To overcome the overfitting on corrupted labels, we propose a novel …
Image classification with deep learning in the presence of noisy labels: A survey
Image classification systems recently made a giant leap with the advancement of deep
neural networks. However, these systems require an excessive amount of labeled data to be …
neural networks. However, these systems require an excessive amount of labeled data to be …
Unsupervised person re-identification: Clustering and fine-tuning
The superiority of deeply learned pedestrian representations has been reported in very
recent literature of person re-identification (re-ID). In this article, we consider the more …
recent literature of person re-identification (re-ID). In this article, we consider the more …
Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning
We focus on the one-shot learning for video-based person re-Identification (re-ID).
Unlabeled tracklets for the person re-ID tasks can be easily obtained by pre-processing …
Unlabeled tracklets for the person re-ID tasks can be easily obtained by pre-processing …
Cost-effective active learning for deep image classification
Recent successes in learning-based image classification, however, heavily rely on the large
number of annotated training samples, which may require considerable human effort. In this …
number of annotated training samples, which may require considerable human effort. In this …