Related papers: Evaluating Input Perturbation Methods for Interpre…

Learning-based methods especially with convolutional neural networks (CNN) are continuously showing superior performance in computer vision applications, ranging from image classification to restoration. For image classification, most…

Currently available methods for extracting saliency maps identify parts of the input which are the most important to a specific fixed classifier. We show that this strong dependence on a given classifier hinders their performance. To…

Saliency detection has been widely studied because it plays an important role in various vision applications, but it is difficult to evaluate saliency systems because each measure has its own bias. In this paper, we first revisit the…

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…

Ground truth for saliency prediction datasets consists of two types of map data: fixation pixel map which records the human eye movements on sample images, and fixation blob map generated by performing gaussian blurring on the corresponding…

Convolutional neural networks (CNNs) define the current state-of-the-art for image recognition. With their emerging popularity, especially for critical applications like medical image analysis or self-driving cars, confirmability is…

Capsule Networks, as alternatives to Convolutional Neural Networks, have been proposed to recognize objects from images. The current literature demonstrates many advantages of CapsNets over CNNs. However, how to create explanations for…

Noise injection is a fundamental tool for data augmentation, and yet there is no widely accepted procedure to incorporate it with learning frameworks. This study analyzes the effects of adding or applying different noise models of varying…

Spatial and intensity normalization are nowadays a prerequisite for neuroimaging analysis. Influenced by voxel-wise and other univariate comparisons, where these corrections are key, they are commonly applied to any type of analysis and…

How do neural network image classifiers respond to simpler and simpler inputs? And what do such responses reveal about the learning process? To answer these questions, we need a clear measure of input simplicity (or inversely, complexity),…

Selective attention is an essential mechanism to filter sensory input and to select only its most important components, allowing the capacity-limited cognitive structures of the brain to process them in detail. The saliency map model,…

Most saliency estimation methods aim to explicitly model low-level conspicuity cues such as edges or blobs and may additionally incorporate top-down cues using face or text detection. Data-driven methods for training saliency models using…

In this paper we propose two saliency models for salient object segmentation based on a hierarchical image segmentation, a tree-like structure that represents regions at different scales from the details to the whole image (e.g. gPb-UCM,…

Topological methods for data analysis present opportunities for enforcing certain invariances of broad interest in computer vision, including view-point in activity analysis, articulation in shape analysis, and measurement invariance 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…

Image classifiers are typically scored on their test set accuracy, but high accuracy can mask a subtle type of model failure. We find that high scoring convolutional neural networks (CNNs) on popular benchmarks exhibit troubling pathologies…

Inverse problems and, in particular, inferring unknown or latent parameters from data are ubiquitous in engineering simulations. A predominant viewpoint in identifying unknown parameters is Bayesian inference where both prior information…

Dozens of new models on fixation prediction are published every year and compared on open benchmarks such as MIT300 and LSUN. However, progress in the field can be difficult to judge because models are compared using a variety of…

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,…

A lack of software reproducibility has become increasingly apparent in the last several years, calling into question the validity of scientific findings affected by published tools. Reproducibility issues may have numerous sources of error,…