相关论文: Explaining an image classifier with a generative m…

Trust is a crucial factor affecting the adoption of machine learning (ML) models. Qualitative studies have revealed that end-users, particularly in the medical domain, need models that can express their uncertainty in decision-making…

In creativity support and computational co-creativity contexts, the task of discovering appropriate prompts for use with text-to-image generative models remains difficult. In many cases the creator wishes to evoke a certain impression with…

Diffusion models have emerged as powerful tools for high-quality image generation and editing, but guiding these models to produce specific outputs remains a challenge. Conventional approaches rely on conditioning mechanisms, such as text…

In this paper, we propose leveraging causal generative learning as an interpretable tool for explaining image classifiers. Specifically, we present a generative counterfactual inference approach to study the influence of visual features…

Clearly explaining a rationale for a classification decision to an end-user can be as important as the decision itself. Existing approaches for deep visual recognition are generally opaque and do not output any justification text;…

Neural networks are prone to learning shortcuts -- they often model simple correlations, ignoring more complex ones that potentially generalize better. Prior works on image classification show that instead of learning a connection to object…

Matching the performance of conditional Generative Adversarial Networks with little supervision is an important task, especially in venturing into new domains. We design a new training algorithm, which is robust to missing or ambiguous…

We present an approach to quantifying both aleatoric and epistemic uncertainty for deep neural networks in image classification, based on generative adversarial networks (GANs). While most works in the literature that use GANs to generate…

In this work, we propose an introspection technique for deep neural networks that relies on a generative model to instigate salient editing of the input image for model interpretation. Such modification provides the fundamental…

Image classification is often prone to labelling uncertainty. To generate suitable training data, images are labelled according to evaluations of human experts. This can result in ambiguities, which will affect subsequent models. In this…

In this paper, we make a bold attempt toward an ambitious task: given a pre-trained classifier, we aim to reconstruct an image generator, without relying on any data samples. From a black-box perspective, this challenge seems intractable,…

Estimating how uncertain an AI system is in its predictions is important to improve the safety of such systems. Uncertainty in predictive can result from uncertainty in model parameters, irreducible data uncertainty and uncertainty due to…

The widespread adoption of generative AI models has raised growing concerns about representational harm and potential discriminatory outcomes. Yet, despite growing literature on this topic, the mechanisms by which bias emerges - especially…

Conditional image modeling based on textual descriptions is a relatively new domain in unsupervised learning. Previous approaches use a latent variable model and generative adversarial networks. While the formers are approximated by using…

Researchers in explainable artificial intelligence have developed numerous methods for helping users understand the predictions of complex supervised learning models. By contrast, explaining the $\textit{uncertainty}$ of model outputs has…

Interpretability and uncertainty quantification in machine learning can provide justification for decisions, promote scientific discovery and lead to a better understanding of model behavior. Symbolic regression provides inherently…

Convolutional image classifiers can achieve high predictive accuracy, but quantifying their uncertainty remains an unresolved challenge, hindering their deployment in consequential settings. Existing uncertainty quantification techniques,…

Quantifying model uncertainty is critical for understanding prediction reliability, yet distinguishing between aleatoric and epistemic uncertainty remains challenging. We extend recent work from classification to regression to provide a…

In recent years, diffusion models have gained popularity for their ability to generate higher-quality images in comparison to GAN models. However, like any other large generative models, these models require a huge amount of data,…

It is well believed that the higher uncertainty in a word of the caption, the more inter-correlated context information is required to determine it. However, current image captioning methods usually consider the generation of all words in a…