Exabytes of data are generated daily by humans, leading to the growing needs for new
efforts in dealing with the grand challenges for multi-label learning brought by big data. For …

Supervised training of deep learning models requires large labeled datasets. There is a
growing interest in obtaining such datasets for medical image analysis applications …

We propose a novel framework to perform classification via deep learning in the presence of
noisy annotations. When trained on noisy labels, deep neural networks have been observed …

We present a simple self-training method that achieves 88.4% top-1 accuracy on ImageNet,
which is 2.0% better than the state-of-the-art model that requires 3.5 B weakly labeled …

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 …

Deep neural networks are known to be annotation-hungry. Numerous efforts have been
devoted to reducing the annotation cost when learning with deep networks. Two prominent …

In facial expression recognition (FER), the uncertainties introduced by inherent noises like
ambiguous facial expressions and inconsistent labels raise concerns about the credibility of …

Training accurate deep neural networks (DNNs) in the presence of noisy labels is an
important and challenging task. Though a number of approaches have been proposed for …

Robust loss functions are essential for training accurate deep neural networks (DNNs) in the
presence of noisy (incorrect) labels. It has been shown that the commonly used Cross …

Existing studies indicate that deep neural networks (DNNs) can eventually memorize the
label noise. We observe that the memorization strength of DNNs towards each instance is …