Related papers: DANCE: Enhancing saliency maps using decoys

Data size is the bottleneck for developing deep saliency models, because collecting eye-movement data is very time consuming and expensive. Most of current studies on human attention and saliency modeling have used high quality stereotype…

Understanding the predictions made by Artificial Intelligence (AI) systems is becoming more and more important as deep learning models are used for increasingly complex and high-stakes tasks. Saliency mapping -- a popular visual attribution…

To investigate the use of saliency-map analysis to aid in searches for transient signals, such as fast radio bursts and individual pulses from radio pulsars. We aim to demonstrate that saliency maps provide the means to understand…

Feature attribution methods, or saliency maps, are one of the most popular approaches for explaining the decisions of complex machine learning models such as deep neural networks. In this study, we propose a stochastic optimization approach…

Pruning unimportant parameters can allow deep neural networks (DNNs) to reduce their heavy computation and memory requirements. A saliency metric estimates which parameters can be safely pruned with little impact on the classification…

Saliency Object Detection (SOD) has several applications in image analysis. The methods have evolved from image-intrinsic to object-inspired (deep-learning-based) models. When a model fail, however, there is no alternative to enhance its…

The volume of User Generated Content (UGC) has increased in recent years. The challenge with this type of content is assessing its quality. So far, the state-of-the-art metrics are not exhibiting a very high correlation with perceptual…

Deep learning dominates image classification tasks, yet understanding how models arrive at predictions remains a challenge. Much research focuses on local explanations of individual predictions, such as saliency maps, which visualise the…

The different families of saliency methods, either based on contrastive signals, closed-form formulas mixing gradients with activations or on perturbation masks, all focus on which parts of an image are responsible for the model's…

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…

Video saliency prediction has recently attracted attention of the research community, as it is an upstream task for several practical applications. However, current solutions are particularly computationally demanding, especially due to the…

Visual saliency prediction using transformers - Convolutional neural networks (CNNs) have significantly advanced computational modelling for saliency prediction. However, accurately simulating the mechanisms of visual attention in the human…

In this paper, we address the problem of quantifying reliability of computational saliency for videos, which can be used to improve saliency-based video processing and enable more reliable performance and risk assessment of such processing.…

We address the issue of visual saliency from three perspectives. First, we consider saliency detection as a frequency domain analysis problem. Second, we achieve this by employing the concept of {\it non-saliency}. Third, we simultaneously…

Gradient-based analysis methods, such as saliency map visualizations and adversarial input perturbations, have found widespread use in interpreting neural NLP models due to their simplicity, flexibility, and most importantly, their…

In this work, we propose to utilize Convolutional Neural Networks to boost the performance of depth-induced salient object detection by capturing the high-level representative features for depth modality. We formulate the depth-induced…

Sampling methods (e.g., node-wise, layer-wise, or subgraph) has become an indispensable strategy to speed up training large-scale Graph Neural Networks (GNNs). However, existing sampling methods are mostly based on the graph structural…

In this paper, an enhancement technique for the class activation mapping methods such as gradient-weighted class activation maps or excitation backpropagation is proposed to present the visual explanations of decisions from convolutional…

Currently available methods for extracting saliency maps identify parts of the input which are the most important to a specific fixed classifier. We show that this strong dependence on a given classifier hinders their performance. To…

Deep learning algorithms lack human-interpretable accounts of how they transform raw visual input into a robust semantic understanding, which impedes comparisons between different architectures, training objectives, and the human brain. In…