Related papers: A Comprehensive Study of Modern Architectures and …

The availability of training data is one of the main limitations in deep learning applications for medical imaging. Data augmentation is a popular approach to overcome this problem. A new approach is a Machine Learning based augmentation,…

This paper introduces AdaptoVision, a novel convolutional neural network (CNN) architecture designed to efficiently balance computational complexity and classification accuracy. By leveraging enhanced residual units, depth-wise separable…

There are not many large medical image datasets available. For these datasets, too small deep learning models can't learn useful features, so they don't work well due to underfitting, and too big models tend to overfit the limited data. As…

Accurate multi-organ segmentation in abdominal CT scans is essential for computer-aided diagnosis and treatment. While convolutional neural networks (CNNs) have long been the standard approach in medical image segmentation,…

We present AURA-net, a convolutional neural network (CNN) for the segmentation of phase-contrast microscopy images. AURA-net uses transfer learning to accelerate training and Attention mechanisms to help the network focus on relevant image…

Background and objective: Cell-level pathological image analysis requires working with extremely small image patches (40x40 pixels), far below standard ImageNet resolutions. It remains unclear whether modern deep learning architectures and…

In many learning situations, resources at inference time are significantly more constrained than resources at training time. This paper studies a general paradigm, called Differentiable ARchitecture Compression (DARC), that combines model…

Pre-training general-purpose visual features with convolutional neural networks without relying on annotations is a challenging and important task. Most recent efforts in unsupervised feature learning have focused on either small or highly…

This study presents a comprehensive comparative analysis of custom-built Convolutional Neural Networks (CNNs) against popular pre-trained architectures (ResNet-18 and VGG-16) using both feature extraction and transfer learning approaches.…

Detection of Alzheimer's Disease (AD) from neuroimaging data such as MRI through machine learning has been a subject of intense research in recent years. Recent success of deep learning in computer vision has progressed such research…

Artificial intelligence has shown significant promise in chest radiography, where deep learning models can approach radiologist-level diagnostic performance. Progress has been accelerated by large public datasets such as MIMIC-CXR,…

In medical image segmentation tasks, the scarcity of labeled training data poses a significant challenge when training deep neural networks. When using U-Net-style architectures, it is common practice to address this problem by pretraining…

Precisely-labeled data sets with sufficient amount of samples are very important for training deep convolutional neural networks (CNNs). However, many of the available real-world data sets contain erroneously labeled samples and those…

The need for large annotated image datasets for training Convolutional Neural Networks (CNNs) has been a significant impediment for their adoption in computer vision applications. We show that with transfer learning an effective object…

Data-augmentation is key to the training of neural networks for image classification. This paper first shows that existing augmentations induce a significant discrepancy between the typical size of the objects seen by the classifier at…

Accurate estimation of predictive uncertainty (model calibration) is essential for the safe application of neural networks. Many instances of miscalibration in modern neural networks have been reported, suggesting a trend that newer, more…

Transfer learning represents a recent paradigm shift in the way we build artificial intelligence (AI) systems. In contrast to training task-specific models, transfer learning involves pre-training deep learning models on a large corpus of…

We introduce ABC-Dataset, a collection of one million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications. Each model is a collection of explicitly parametrized curves and surfaces, providing…

Despite tremendous progress in developing deep-learning-based weather forecasting systems, their design space, including the impact of different design choices, is yet to be well understood. This paper aims to fill this knowledge gap by…

Convolutional neural networks for visual recognition require large amounts of training samples and usually benefit from data augmentation. This paper proposes PatchMix, a data augmentation method that creates new samples by composing…