Related papers: Explaining neural network predictions of material …

One of the most crucial tasks in seismic reflection imaging is to identify the salt bodies with high precision. Traditionally, this is accomplished by visually picking the salt/sediment boundaries, which requires a great amount of manual…

Recently, many methods to interpret and visualize deep neural network predictions have been proposed and significant progress has been made. However, a more class-discriminative and visually pleasing explanation is required. Thus, this…

There has been profound progress in visual saliency thanks to the deep learning architectures, however, there still exist three major challenges that hinder the detection performance for scenes with complex compositions, multiple salient…

Adversarial images highlight how vulnerable modern image classifiers are to perturbations outside of their training set. Human oversight might mitigate this weakness, but depends on humans understanding the AI well enough to predict when it…

Machine learning (ML) based materials discovery has emerged as one of the most promising approaches for breakthroughs in materials science. While heuristic knowledge based descriptors have been combined with ML algorithms to achieve good…

The prediction of salient areas in images has been traditionally addressed with hand-crafted features based on neuroscience principles. This paper, however, addresses the problem with a completely data-driven approach by training a…

Neural networks for computer vision extract uninterpretable features despite achieving high accuracy on benchmarks. In contrast, humans can explain their predictions using succinct and intuitive descriptions. To incorporate explainability…

Multi-technique high resolution X-ray mapping enhanced by the recent advent of 4th generation synchrotron facilities can produce colossal datasets, challenging traditional analysis methods. Such difficulty is clearly materialized when…

Flow-Imaging Microscopy (FIM) is commonly used in both academia and industry to characterize subvisible particles (those $\le 25 \mu m$ in size) in protein therapeutics. Pharmaceutical companies are required to record vast volumes of FIM…

It has long been considered a significant problem to improve the visual quality of lossy image and video compression. Recent advances in computing power together with the availability of large training data sets has increased interest in…

In this work, we try to address the challenging problem of dimple detection and segmentation in Titanium alloys using machine learning methods, especially neural networks. The images i.e. fractographs are obtained using a Scanning Election…

In this project, a state-of-the-art deep convolution neural network (DCNN) is presented to segment seismic images for salt detection below the earth's surface. Detection of salt location is very important for starting mining. Hence, a…

There has long been debates on how we could interpret neural networks and understand the decisions our models make. Specifically, why deep neural networks tend to be error-prone when dealing with samples that output low softmax scores. We…

The design of novel materials hinges on the understanding of structure-property relationships. However, in recent times, our capability to synthesize a large number of materials has outpaced our speed at characterizing them. While the…

Recent advances in saliency detection have utilized deep learning to obtain high level features to detect salient regions in a scene. These advances have demonstrated superior results over previous works that utilize hand-crafted low level…

In medical imaging, particularly in early disease detection and prognosis tasks, discerning the rationale behind an AI model's predictions is crucial for evaluating the reliability of its decisions. Conventional explanation methods face…

Due to their ability to recognize complex patterns, neural networks can drive a paradigm shift in the analysis of materials science data. Here, we introduce ARISE, a crystal-structure identification method based on Bayesian deep learning.…

Despite the tremendous achievements of deep convolutional neural networks (CNNs) in many computer vision tasks, understanding how they actually work remains a significant challenge. In this paper, we propose a novel two-step understanding…

Saliency prediction is a well studied problem in computer vision. Early saliency models were based on low-level hand-crafted feature derived from insights gained in neuroscience and psychophysics. In the wake of deep learning breakthrough,…

We report resolution enhancement in scanning electron microscopy (SEM) images using a generative adversarial network. We demonstrate the veracity of this deep learning-based super-resolution technique by inferring unresolved features in…