相关论文: Saliency Cards: A Framework to Characterize and Co…

Since the early 2000s, computational visual saliency has been a very active research area. Each year, more and more new models are published in the main computer vision conferences. Nowadays, one of the big challenges is to find a way to…

Saliency methods -- techniques to identify the importance of input features on a model's output -- are a common step in understanding neural network behavior. However, interpreting saliency requires tedious manual inspection to identify and…

Saliency methods are used extensively to highlight the importance of input features in model predictions. These methods are mostly used in vision and language tasks, and their applications to time series data is relatively unexplored. In…

Saliency maps have become a widely used method to make deep learning models more interpretable by providing post-hoc explanations of classifiers through identification of the most pertinent areas of the input medical image. They are…

Understanding specifically where a model focuses on within an image is critical for human interpretability of the decision-making process. Deep learning-based solutions are prone to learning coincidental correlations in training datasets,…

Saliency methods can make deep neural network predictions more interpretable by identifying a set of critical features in an input sample, such as pixels that contribute most strongly to a prediction made by an image classifier.…

Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly align with semantically meaningful input features. We argue that a fundamental cause of…

In high-stakes applications of machine learning models, interpretability methods provide guarantees that models are right for the right reasons. In medical imaging, saliency maps have become the standard tool for determining whether a…

Saliency methods seek to explain the predictions of a model by producing an importance map across each input sample. A popular class of such methods is based on backpropagating a signal and analyzing the resulting gradient. Despite much…

Saliency methods have been widely used to highlight important input features in model predictions. Most existing methods use backpropagation on a modified gradient function to generate saliency maps. Thus, noisy gradients can result in…

Previous saliency detection research required the reader to evaluate performance qualitatively, based on renderings of saliency maps on a few shapes. This qualitative approach meant it was unclear which saliency models were better, or how…

One of the significant challenges of deep neural networks is that the complex nature of the network prevents human comprehension of the outcome of the network. Consequently, the applicability of complex machine learning models is limited in…

Saliency methods are a popular class of feature attribution explanation methods that aim to capture a model's predictive reasoning by identifying "important" pixels in an input image. However, the development and adoption of these methods…

Learning computational models for visual attention (saliency estimation) is an effort to inch machines/robots closer to human visual cognitive abilities. Data-driven efforts have dominated the landscape since the introduction of deep neural…

For more than a decade, deep learning models have been dominating in various 2D imaging tasks. Their application is now extending to 3D imaging, with 3D Convolutional Neural Networks (3D CNNs) being able to process LIDAR, MRI, and CT scans,…

While a lot of research in explainable AI focuses on producing effective explanations, less work is devoted to the question of how people understand and interpret the explanation. In this work, we focus on this question through a study of…

Incorporating human-perceptual intelligence into model training has shown to increase the generalization capability of models in several difficult biometric tasks, such as presentation attack detection (PAD) and detection of synthetic…

While there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation datasets and metrics. In this paper, we present a novel…

High-quality saliency maps are essential in several machine learning application areas including explainable AI and weakly supervised object detection and segmentation. Many techniques have been developed to generate better saliency using…

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…