相关论文: Evaluating Input Perturbation Methods for Interpre…

Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been…

Inputs to machine learning models can have associated noise or uncertainties, but they are often ignored and not modelled. It is unknown if Bayesian Neural Networks and their approximations are able to consider uncertainty in their inputs.…

Within high-performance computing (HPC), solving large sparse linear systems efficiently remains paramount, with iterative methods being the predominant choice. However, the performance of these methods is tightly coupled to the aptness of…

Many algorithms and observed phenomena in deep learning appear to be affected by parameter symmetries -- transformations of neural network parameters that do not change the underlying neural network function. These include linear mode…

Although neural networks perform very well on the image classification task, they are still vulnerable to adversarial perturbations that can fool a neural network without visibly changing an input image. A paper has shown the existence of…

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with…

The black-box nature of Deep Neural Networks (DNNs) severely hinders its performance improvement and application in specific scenes. In recent years, class activation mapping-based method has been widely used to interpret the internal…

This paper proposes a new end-to-end trainable model for lossy image compression, which includes several novel components. The method incorporates 1) an adequate perceptual similarity metric; 2) saliency in the images; 3) a hierarchical…

Bayesian neural networks (BNNs) have recently regained a significant amount of attention in the deep learning community due to the development of scalable approximate Bayesian inference techniques. There are several advantages of using a…

This paper studies causal inference with observational data from a single large network. We consider a nonparametric model with interference in both potential outcomes and selection into treatment. Specifically, both stages may be the…

Cross-modality image estimation involves the generation of images of one medical imaging modality from that of another modality. Convolutional neural networks (CNNs) have been shown to be useful in identifying, characterising and extracting…

In this work, we investigate the value of uncertainty modeling in 3D super-resolution with convolutional neural networks (CNNs). Deep learning has shown success in a plethora of medical image transformation problems, such as…

A deep feature based saliency model (DeepFeat) is developed to leverage the understanding of the prediction of human fixations. Traditional saliency models often predict the human visual attention relying on few level image cues. Although…

Recently, methods based on Convolutional Neural Networks (CNN) achieved impressive success in semantic segmentation tasks. However, challenges such as the class imbalance and the uncertainty in the pixel-labeling process are not completely…

Deep neural networks have demonstrated superior performance in artificial intelligence applications, but the opaqueness of their inner working mechanism is one major drawback in their application. The prevailing unit-based interpretation is…

The explainability of deep learning models remains a significant challenge, particularly in the medical domain where interpretable outputs are essential for clinical trust and transparency. Path attribution methods such as Integrated…

Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using…

The success of current deep saliency detection methods heavily depends on the availability of large-scale supervision in the form of per-pixel labeling. Such supervision, while labor-intensive and not always possible, tends to hinder the…

Loss-gradients are used to interpret the decision making process of deep learning models. In this work, we evaluate loss-gradient based attribution methods by occluding parts of the input and comparing the performance of the occluded input…

A problem of image denoising when images are corrupted by a non-stationary noise is considered in this paper. Since in practice no a priori information on noise is available, noise statistics should be pre-estimated for image denoising. In…