相关论文: Go Figure: Transparency in neuroscience images pre…

The reproducibility of scientific research has become a point of critical concern. We argue that openness and transparency are critical for reproducibility, and we outline an ecosystem for open and transparent science that has emerged…

Explainability is an essential reason limiting the application of neural networks in many vital fields. Although neuro-symbolic AI hopes to enhance the overall explainability by leveraging the transparency of symbolic learning, the results…

Deep learning methods have become very popular for the processing of natural images, and were then successfully adapted to the neuroimaging field. As these methods are non-transparent, interpretability methods are needed to validate them…

Neuroimaging has profoundly enhanced our understanding of the human brain by characterizing its structure, function, and connectivity through modalities like MRI, fMRI, EEG, and PET. These technologies have enabled major breakthroughs…

Artificial Intelligence has emerged as a useful aid in numerous clinical applications for diagnosis and treatment decisions. Deep neural networks have shown same or better performance than clinicians in many tasks owing to the rapid…

Visualisation facilitates the understanding of scientific data both through exploration and explanation of visualised data. Provenance contributes to the understanding of data by containing the contributing factors behind a result. With the…

Implicit neural representations (INRs) have gained prominence as a powerful paradigm in scene reconstruction and computer graphics, demonstrating remarkable results. By utilizing neural networks to parameterize data through implicit…

Transparent object perception is a rapidly developing research problem in artificial intelligence. The ability to perceive transparent objects enables robots to achieve higher levels of autonomy, unlocking new applications in various…

Deep learning methods have recently made notable advances in the tasks of classification and representation learning. These tasks are important for brain imaging and neuroscience discovery, making the methods attractive for porting to a…

As artificial intelligence systems increasingly inform high-stakes decisions across sectors, transparency has become foundational to responsible and trustworthy AI implementation. Leveraging our role as a leading institute in advancing AI…

Deep learning has become popular because of its potential to achieve high accuracy in prediction tasks. However, accuracy is not always the only goal of statistical modelling, especially for models developed as part of scientific research.…

Procedural models (i.e. symbolic programs that output visual data) are a historically-popular method for representing graphics content: vegetation, buildings, textures, etc. They offer many advantages: interpretable design parameters,…

Deep learning has driven significant advances in medical image analysis, yet its adoption in clinical practice remains constrained by the large size and lack of transparency in modern models. Advances in interpretability techniques such as…

Boundary samples are special inputs to artificial neural networks crafted to identify the execution environment used for inference by the resulting output label. The paper presents and evaluates algorithms to generate transparent boundary…

Thresholding converts a greyscale image into a binary image, and is thus often a necessary segmentation step in image processing. For a human viewer however, thresholding usually has a negative impact on the legibility of document images.…

As researchers strive to narrow the gap between machine intelligence and human through the development of artificial intelligence technologies, it is imperative that we recognize the critical importance of trustworthiness in open-world,…

Deep neural networks have proven to be very effective for computer vision tasks, such as image classification, object detection, and semantic segmentation -- these are primarily applied to color imagery and video. In recent years, there has…

Although self-supervised learning enables us to bootstrap the training by exploiting unlabeled data, the generic self-supervised methods for natural images do not sufficiently incorporate the context. For medical images, a desirable method…

As interpretability has been pointed out as the obstacle to the adoption of Deep Neural Networks (DNNs), there is an increasing interest in solving a transparency issue to guarantee the impressive performance. In this paper, we demonstrate…

Recently there has been a significant interest in learning disentangled representations, as they promise increased interpretability, generalization to unseen scenarios and faster learning on downstream tasks. In this paper, we investigate…