相关论文: Saliency Map Verbalization: Comparing Feature Impo…

Recent work uncovered potential flaws in \eg attribution or heatmap based saliency methods. A typical flaw is a confirmations bias, where the scores are compared to human expectation. Since measuring the quality of saliency methods is hard…

We present a novel method for reliably explaining the predictions of neural networks. We consider an explanation reliable if it identifies input features relevant to the model output by considering the input and the neighboring data points.…

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…

Methods based on class activation maps (CAM) provide a simple mechanism to interpret predictions of convolutional neural networks by using linear combinations of feature maps as saliency maps. By contrast, masking-based methods optimize a…

The expansion of explainable artificial intelligence as a field of research has generated numerous methods of visualizing and understanding the black box of a machine learning model. Attribution maps are generally used to highlight the…

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…

Saliency is the perceptual capacity of our visual system to focus our attention (i.e. gaze) on relevant objects. Neural networks for saliency estimation require ground truth saliency maps for training which are usually achieved via…

Identifying the salience (i.e. importance) of discourse units is an important task in language understanding. While events play important roles in text documents, little research exists on analyzing their saliency status. This paper…

Interpretable machine learning and explainable artificial intelligence have become essential in many applications. The trade-off between interpretability and model performance is the traitor to developing intrinsic and model-agnostic…

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…

In this paper, we propose a data-free method of extracting Impressions of each class from the classifier's memory. The Deep Learning regime empowers classifiers to extract distinct patterns (or features) of a given class from training data,…

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…

The field of eXplainable artificial intelligence (XAI) has produced a plethora of methods (e.g., saliency-maps) to gain insight into artificial intelligence (AI) models, and has exploded with the rise of deep learning (DL). However,…

Word-level saliency explanations ("heat maps over words") are often used to communicate feature-attribution in text-based models. Recent studies found that superficial factors such as word length can distort human interpretation of the…

Saliency maps can explain how deep neural networks classify images. But are they actually useful for humans? The present systematic review of 68 user studies found that while saliency maps can enhance human performance, null effects or even…

Most of the saliency methods are evaluated on their ability to generate saliency maps, and not on their functionality in a complete vision pipeline, like for instance, image classification. In the current paper, we propose an approach which…

Existing saliency-guided training approaches improve model generalization by incorporating a loss term that compares the model's class activation map (CAM) for a sample's true-class ({\it i.e.}, correct-label class) against a human…

Determining the relative importance of the elements in a sentence is a key factor for effortless natural language understanding. For human language processing, we can approximate patterns of relative importance by measuring reading…

Neural image/video captioning models can generate accurate descriptions, but their internal process of mapping regions to words is a black box and therefore difficult to explain. Top-down neural saliency methods can find important regions…

Traditional saliency map methods, popularized in computer vision, highlight individual points (pixels) of the input that contribute the most to the model's output. However, in time series, they offer limited insights, as semantically…