相关论文: A Human-Grounded Evaluation Benchmark for Local Ex…

Clinical applicability of automated decision support systems depends on a robust, well-understood classification interpretation. Artificial neural networks while achieving class-leading scores fall short in this regard. Therefore, numerous…

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…

There is a recent surge of interest in using attention as explanation of model predictions, with mixed evidence on whether attention can be used as such. While attention conveniently gives us one weight per input token and is easily…

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…

The human visual system employs a selective attention mechanism to understand the visual world in an eficient manner. In this paper, we show how computational models of this mechanism can be exploited for the computer vision application of…

Determining and ranking the most salient entities in a text is critical for user-facing systems, especially as users increasingly rely on models to interpret long documents they only partially read. Graded entity salience addresses this…

In the realm of image synthesis, achieving fidelity to a reference image while adhering to conditional prompts remains a significant challenge. This paper proposes a novel approach that integrates a diffusion model with latent space…

This paper studies the task of matching image and sentence, where learning appropriate representations across the multi-modal data appears to be the main challenge. Unlike previous approaches that predominantly deploy symmetrical…

Argument mining is a core technology for automating argument search in large document collections. Despite its usefulness for this task, most current approaches to argument mining are designed for use only with specific text types and fall…

In mission-critical domains such as law enforcement and medical diagnosis, the ability to explain and interpret the outputs of deep learning models is crucial for ensuring user trust and supporting informed decision-making. Despite…

Since the early 2000s, computational visual saliency has been a very active research area. Each year, more and more new models are published in the main computer vision conferences. Nowadays, one of the big challenges is to find a way to…

Salient object detection is evaluated using binary ground truth with the labels being salient object class and background. In this paper, we corroborate based on three subjective experiments on a novel image dataset that objects in natural…

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…

With the increased focus on visual attention (VA) in the last decade, a large number of computational visual saliency methods have been developed over the past few years. These models are traditionally evaluated by using performance…

Attention mechanisms have recently been introduced in deep learning for various tasks in natural language processing and computer vision. But despite their popularity, the "correctness" of the implicitly-learned attention maps has only been…

Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work,…

The attention mechanisms in deep neural networks are inspired by human's attention that sequentially focuses on the most relevant parts of the information over time to generate prediction output. The attention parameters in those models are…

The saliency ranking task is recently proposed to study the visual behavior that humans would typically shift their attention over different objects of a scene based on their degrees of saliency. Existing approaches focus on learning either…

Large pre-trained language models have achieved impressive results on various style classification tasks, but they often learn spurious domain-specific words to make predictions (Hayati et al., 2021). While human explanation highlights…

Automatically generating a human-like description for a given image is a potential research in artificial intelligence, which has attracted a great of attention recently. Most of the existing attention methods explore the mapping…