Related papers: Investigating sanity checks for saliency maps with…

Despite strong performance of Multimodal Large Language Models (MLLMs) on multimodal tasks, predicting whether and why an image is persuasive remains challenging. We first show that prompting MLLMs to reason before prediction does not…

The growing capabilities of AI models are leading to their wider use, including in safety-critical domains. Explainable AI (XAI) aims to make these models safer to use by making their inference process more transparent. However, current…

We introduce a saliency-based distortion layer for convolutional neural networks that helps to improve the spatial sampling of input data for a given task. Our differentiable layer can be added as a preprocessing block to existing task…

Post-hoc saliency methods are widely used to interpret deep neural networks, but their faithfulness is difficult to evaluate reliably. Existing evaluations mask features according to saliency-induced feature ordering and measure performance…

Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the probability of each prediction to approach a 0-1 distribution.…

In this work we develop a fast saliency detection method that can be applied to any differentiable image classifier. We train a masking model to manipulate the scores of the classifier by masking salient parts of the input image. Our model…

We present a randomized controlled trial for a model-in-the-loop regression task, with the goal of measuring the extent to which (1) good explanations of model predictions increase human accuracy, and (2) faulty explanations decrease human…

Deep Neural Networks are powerful tools to understand complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. While online saliency-guided training methods try to…

As Deep Neural Network models for face processing tasks approach human-like performance, their deployment in critical applications such as law enforcement and access control has seen an upswing, where any failure may have far-reaching…

This paper presents a fresh perspective on the role of saliency maps in weakly-supervised semantic segmentation (WSSS) and offers new insights and research directions based on our empirical findings. We conduct comprehensive experiments and…

Adversarial attacks pose a significant challenge to deploying deep learning models in safety-critical applications. Maintaining model robustness while ensuring interpretability is vital for fostering trust and comprehension in these models.…

We propose a framework inspired by biological vision systems to produce saliency maps of digital images. Well-known computational models for receptive fields of areas in the visual cortex that are specialized for color and orientation…

In recent years, considerable work has been devoted to explaining predictive, deep learning-based models, and in turn how to evaluate explanations. An important class of evaluation methods are ones that are human-centered, which typically…

With recent advances in deep learning, neuroimaging studies increasingly rely on convolutional networks (ConvNets) to predict diagnosis based on MR images. To gain a better understanding of how a disease impacts the brain, the studies…

Natural Language Inference is a challenging task that has received substantial attention, and state-of-the-art models now achieve impressive test set performance in the form of accuracy scores. Here, we go beyond this single evaluation…

Statistical significance testing is used in natural language processing (NLP) to determine whether the results of a study or experiment are likely to be due to chance or if they reflect a genuine relationship. A key step in significance…

In this paper, we address the problem of quantifying reliability of computational saliency for videos, which can be used to improve saliency-based video processing and enable more reliable performance and risk assessment of such processing.…

The black-box nature of the deep networks makes the explanation for "why" they make certain predictions extremely challenging. Saliency maps are one of the most widely-used local explanation tools to alleviate this problem. One of the…

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…

Results of neural network learning are always subject to some variability, due to the sensitivity to initial conditions, to convergence to local minima, and, sometimes more dramatically, to sampling variability. This paper presents a set of…