Related papers: SaliencyDecor: Enhancing Neural Network Interpreta…

In recent years, deep saliency models have made significant progress in predicting human visual attention. However, the mechanisms behind their success remain largely unexplained due to the opaque nature of deep neural networks. In this…

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…

Saliency maps can explain a neural model's predictions by identifying important input features. They are difficult to interpret for laypeople, especially for instances with many features. In order to make them more accessible, we formalize…

Image captioning has been recently gaining a lot of attention thanks to the impressive achievements shown by deep captioning architectures, which combine Convolutional Neural Networks to extract image representations, and Recurrent Neural…

A popular approach to unveiling the black box of neural NLP models is to leverage saliency methods, which assign scalar importance scores to each input component. A common practice for evaluating whether an interpretability method is…

In this paper, we introduce a strategy for identifying textual saliency in large-scale language models applied to classification tasks. In visual networks where saliency is more well-studied, saliency is naturally localized through the…

Recent efforts to improve the interpretability of deep neural networks use saliency to characterize the importance of input features to predictions made by models. Work on interpretability using saliency-based methods on Recurrent Neural…

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…

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…

To detect salient objects accurately, existing methods usually design complex backbone network architectures to learn and fuse powerful features. However, the saliency inference module that performs saliency prediction from the fused…

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…

Recent advances in saliency detection have utilized deep learning to obtain high level features to detect salient regions in a scene. These advances have demonstrated superior results over previous works that utilize hand-crafted low level…

This paper presents a novel deep architecture for saliency prediction. Current state of the art models for saliency prediction employ Fully Convolutional networks that perform a non-linear combination of features extracted from the last…

Deep convolutional neural networks (CNNs) have delivered superior performance in many computer vision tasks. In this paper, we propose a novel deep fully convolutional network model for accurate salient object detection. The key…

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,…

Deep convolutional neural networks have achieved impressive performance on a broad range of problems, beating prior art on established benchmarks, but it often remains unclear what are the representations learnt by those systems and how…

Feed-forward only convolutional neural networks (CNNs) may ignore intrinsic relationships and potential benefits of feedback connections in vision tasks such as saliency detection, despite their significant representation capabilities. In…

Predicting salient regions in natural images requires the detection of objects that are present in a scene. To develop robust representations for this challenging task, high-level visual features at multiple spatial scales must be extracted…

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…

Transparency and explainability in image classification are essential for establishing trust in machine learning models and detecting biases and errors. State-of-the-art explainability methods generate saliency maps to show where a specific…