Related papers: Forward Learning for Gradient-based Black-box Sali…

Input gradients have a pivotal role in a variety of applications, including adversarial attack algorithms for evaluating model robustness, explainable AI techniques for generating Saliency Maps, and counterfactual explanations.However,…

The Convolutional Neural Network (CNN) is a widely used deep learning architecture for computer vision. However, its black box nature makes it difficult to interpret the behavior of the model. To mitigate this issue, AI practitioners have…

The recent success of immersive applications is pushing the research community to define new approaches to process 360{\deg} images and videos and optimize their transmission. Among these, saliency estimation provides a powerful tool that…

The black-box nature of neural networks limits model decision interpretability, in particular for high-dimensional inputs in computer vision and for dense pixel prediction tasks like segmentation. To address this, prior work combines neural…

The correct interpretation of convolutional models is a hard problem for time series data. While saliency methods promise visual validation of predictions for image and language processing, they fall short when applied to time series. These…

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…

Saliency detection aims to detect the most attractive objects in images and is widely used as a foundation for various applications. In this paper, we propose a novel salient object detection algorithm for RGB-D images using center-dark…

Deep learning models have performed well on many NLP tasks. However, their internal mechanisms are typically difficult for humans to understand. The development of methods to explain models has become a key issue in the reliability of deep…

Integrated gradients is prevalent within machine learning to address the black-box problem of neural networks. The explanations given by integrated gradients depend on a choice of base-point. The choice of base-point is not a priori obvious…

We propose a technique for producing "visual explanations" for decisions from a large class of CNN-based models, making them more transparent. Our approach - Gradient-weighted Class Activation Mapping (Grad-CAM), uses the gradients of any…

The classification of the optical spectra of active galactic nuclei (AGN) into different types is well founded on AGN physics, but it involves some degree of human oversight and cannot be reliably scaled to large data sets. Machine learning…

Recent results suggest that state-of-the-art saliency models perform far from optimal in predicting fixations. This lack in performance has been attributed to an inability to model the influence of high-level image features such as objects.…

While stochastic variational inference is relatively well known for scaling inference in Bayesian probabilistic models, related methods also offer ways to circumnavigate the approximation of analytically intractable expectations. The key…

We introduce a new tool for interpreting neural net responses, namely full-gradients, which decomposes the neural net response into input sensitivity and per-neuron sensitivity components. This is the first proposed representation which…

Saliency maps are widely used for visual explanations in deep learning, but a fundamental lack of consensus persists regarding their intended purpose and alignment with diverse user queries. This ambiguity hinders the effective evaluation…

To date, several methods have been developed to explain deep learning algorithms for classification tasks. Recently, an adaptation of two of such methods has been proposed to generate instance-level explainable maps in a semantic…

As prior knowledge of objects or object features helps us make relations for similar objects on attentional tasks, pre-trained deep convolutional neural networks (CNNs) can be used to detect salient objects on images regardless of the…

Practitioners apply neural networks to increasingly complex problems in natural language processing, such as syntactic parsing and semantic role labeling that have rich output structures. Many such structured-prediction problems require…

Saliency maps have proven to be a highly efficacious approach for explicating the decisions of Convolutional Neural Networks. However, extant methodologies predominantly rely on gradients, which constrain their ability to explicate complex…

Predicting saliency in videos is a challenging problem due to complex modeling of interactions between spatial and temporal information, especially when ever-changing, dynamic nature of videos is considered. Recently, researchers have…