相关论文: AdViCE: Aggregated Visual Counterfactual Explanati…

Transparency is an essential requirement of machine learning based decision making systems that are deployed in real world. Often, transparency of a given system is achieved by providing explanations of the behavior and predictions of the…

Visual counterfactual explanations (VCEs) in image space are an important tool to understand decisions of image classifiers as they show under which changes of the image the decision of the classifier would change. Their generation in image…

There is a growing trend of applying machine learning methods to medical datasets in order to predict patients' future status. Although some of these methods achieve high performance, challenges still exist in comparing and evaluating…

Artificial intelligence, particularly through recent advancements in deep learning, has achieved exceptional performances in many tasks in fields such as natural language processing and computer vision. In addition to desirable evaluation…

It is commonly believed that increasing the interpretability of a machine learning model may decrease its predictive power. However, inspecting input-output relationships of those models using visual analytics, while treating them as…

Machines are being increasingly used in decision-making processes, resulting in the realization that decisions need explanations. Unfortunately, an increasing number of these deployed models are of a 'black-box' nature where the reasoning…

Deep Learning algorithms are often used as black box type learning and they are too complex to understand. The widespread usability of Deep Learning algorithms to solve various machine learning problems demands deep and transparent…

Vision-language models (VLMs) exhibit a systematic bias when confronted with classic optical illusions: they overwhelmingly predict the illusion as "real" regardless of whether the image has been counterfactually modified. We present a…

The promise of multimodal models for real-world applications has inspired research in visualizing and understanding their internal mechanics with the end goal of empowering stakeholders to visualize model behavior, perform model debugging,…

With the widespread consumption of AI-generated content, there has been an increased focus on developing automated tools to verify the factual accuracy of such content. However, prior research and tools developed for fact verification treat…

Confidence scores of automatic speech recognition (ASR) outputs are often inadequately communicated, preventing its seamless integration into analytical workflows. In this paper, we introduce ConFides, a visual analytic system developed in…

Recent work on counterfactual visual explanations has contributed to making artificial intelligence models more explainable by providing visual perturbation to flip the prediction. However, these approaches neglect the causal relationships…

Recent black-box counterfactual generation frameworks fail to take into account the semantic content of the proposed edits, while relying heavily on training to guide the generation process. We propose a novel, plug-and-play black-box…

Counterfactual reasoning -- the practice of asking ``what if'' by varying inputs and observing changes in model behavior -- has become central to interpretable and fair AI. This thesis develops frameworks that use counterfactuals to…

Explanation of AI, as well as fairness of algorithms' decisions and the transparency of the decision model, are becoming more and more important. And it is crucial to design effective and human-friendly techniques when opening the black-box…

Data-driven decision making related to individuals has become increasingly pervasive, but the issue concerning the potential discrimination has been raised by recent studies. In response, researchers have made efforts to propose and…

ConvNets and Imagenet have driven the recent success of deep learning for image classification. However, the marked slowdown in performance improvement combined with the lack of robustness of neural networks to adversarial examples and…

As artificial intelligence plays an increasingly important role in our society, there are ethical and moral obligations for both businesses and researchers to ensure that their machine learning models are designed, deployed, and maintained…

Neural Sequence-to-Sequence models have proven to be accurate and robust for many sequence prediction tasks, and have become the standard approach for automatic translation of text. The models work in a five stage blackbox process that…

A key step in the Bayesian workflow for model building is the graphical assessment of model predictions, whether these are drawn from the prior or posterior predictive distribution. The goal of these assessments is to identify whether the…