相关论文: Where do Models go Wrong? Parameter-Space Saliency…

Saliency methods aim to explain the predictions of deep neural networks. These methods lack reliability when the explanation is sensitive to factors that do not contribute to the model prediction. We use a simple and common pre-processing…

The performance of convolutional neural networks has continued to improve over the last decade. At the same time, as model complexity grows, it becomes increasingly more difficult to explain model decisions. Such explanations may be of…

A fundamental bottleneck in utilising complex machine learning systems for critical applications has been not knowing why they do and what they do, thus preventing the development of any crucial safety protocols. To date, no method exist…

Saliency methods have emerged as a popular tool to highlight features in an input deemed relevant for the prediction of a learned model. Several saliency methods have been proposed, often guided by visual appeal on image data. In this work,…

With their increase in performance, neural network architectures also become more complex, necessitating explainability. Therefore, many new and improved methods are currently emerging, which often generate so-called saliency maps in order…

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.…

Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions. However, saliency maps are often visually noisy. Although several hypotheses were…

Saliency methods provide post-hoc model interpretation by attributing input features to the model outputs. Current methods mainly achieve this using a single input sample, thereby failing to answer input-independent inquiries about the…

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…

Convolutional neural networks (CNNs) are commonly used for image classification. Saliency methods are examples of approaches that can be used to interpret CNNs post hoc, identifying the most relevant pixels for a prediction following the…

Poor generalization is one symptom of models that learn to predict target variables using spuriously-correlated image features present only in the training distribution instead of the true image features that denote a class. It is often…

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 prediction is a well studied problem in computer vision. Early saliency models were based on low-level hand-crafted feature derived from insights gained in neuroscience and psychophysics. In the wake of deep learning breakthrough,…

The classification decisions of neural networks can be misled by small imperceptible perturbations. This work aims to explain the misled classifications using saliency methods. The idea behind saliency methods is to explain the…

Deep neural networks are being increasingly implemented throughout society in recent years. It is useful to identify which parameters trigger misclassification in diagnosing undesirable model behaviors. The concept of parameter saliency is…

Saliency methods are widely used to interpret neural network predictions, but different variants of saliency methods often disagree even on the interpretations of the same prediction made by the same model. In these cases, how do we…

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…

Graph Neural Networks (GNNs) have gained prominence for their ability to process graph-structured data across various domains. However, interpreting GNN decisions remains a significant challenge, leading to the adoption of saliency maps for…

Explaining a deep learning model can help users understand its behavior and allow researchers to discern its shortcomings. Recent work has primarily focused on explaining models for tasks like image classification or visual question…

Saliency methods are a common class of machine learning interpretability techniques that calculate how important each input feature is to a model's output. We find that, with the rapid pace of development, users struggle to stay informed of…