Related papers: Maximum Entropy on Erroneous Predictions (MEEP): I…

Incremental learning of semantic segmentation has emerged as a promising strategy for visual scene interpretation in the open- world setting. However, it remains challenging to acquire novel classes in an online fashion for the segmentation…

Traditional supervised medical image segmentation models require large amounts of labeled data for training; however, obtaining such large-scale labeled datasets in the real world is extremely challenging. Recent semi-supervised…

The minimum error entropy (MEE) criterion has been verified as a powerful approach for non-Gaussian signal processing and robust machine learning. However, the implementation of MEE on robust classification is rather a vacancy in the…

Machine learning classifiers often produce probabilistic predictions that are critical for accurate and interpretable decision-making in various domains. The quality of these predictions is generally evaluated with proper losses, such as…

Parameter estimation in Markov random fields (MRFs) is a difficult task, in which inference over the network is run in the inner loop of a gradient descent procedure. Replacing exact inference with approximate methods such as loopy belief…

Deep convolutional neural networks (CNNs), especially fully convolutional networks, have been widely applied to automatic medical image segmentation problems, e.g., multi-organ segmentation. Existing CNN-based segmentation methods mainly…

Region-based methods have proven necessary for improving segmentation accuracy of neuronal structures in electron microscopy (EM) images. Most region-based segmentation methods use a scoring function to determine region merging. Such…

Delivering meaningful uncertainty estimates is essential for a successful deployment of machine learning models in the clinical practice. A central aspect of uncertainty quantification is the ability of a model to return predictions that…

Supervised learning has proved effective for medical image analysis. However, it can utilize only the small labeled portion of data; it fails to leverage the large amounts of unlabeled data that is often available in medical image datasets.…

Probability calibration for deep models is highly desirable in safety-critical applications such as medical imaging. It makes output probabilities of deep networks interpretable, by aligning prediction probability with the actual accuracy…

The application of standard sufficient dimension reduction methods for reducing the dimension space of predictors without losing regression information requires inverting the covariance matrix of the predictors. This has posed a number of…

Self-training is a powerful approach to deep learning. The key process is to find a pseudo-label for modeling. However, previous self-training algorithms suffer from the over-confidence issue brought by the hard labels, even some…

We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost---to improve generalization of deep learning for potentially…

Automated segmentation of anatomical sub-regions with high precision has become a necessity to enable the quantification and characterization of cells/ tissues in histology images. Currently, a machine learning model to analyze…

Robustness to bit errors is a key requirement for the reliable use of neural networks (NNs) on emerging approximate computing platforms and error-prone memory technologies. A common approach to achieve bit error tolerance in NNs is…

Medical image segmentation is one of the fundamental problems for artificial intelligence-based clinical decision systems. Current automatic medical image segmentation methods are often failed to meet clinical requirements. As such, a…

Deep networks have enabled reinforcement learning to scale to more complex and challenging domains, but these methods typically require large quantities of training data. An alternative is to use sample-efficient episodic control methods:…

Deep learning has been widely accepted as a promising solution for medical image segmentation, given a sufficiently large representative dataset of images with corresponding annotations. With ever increasing amounts of annotated medical…

Convolutional neural networks (CNNs) trained with cross-entropy loss have proven to be extremely successful in classifying images. In recent years, much work has been done to also improve the theoretical understanding of neural networks.…

Model calibration aims to align confidence with prediction correctness. The Cross-Entropy (CE) loss is widely used for calibrator training, which enforces the model to increase confidence on the ground truth class. However, we find the CE…