Related papers: ESCAPE: Countering Systematic Errors from Machine'…

The problem of open-set noisy labels denotes that part of training data have a different label space that does not contain the true class. Lots of approaches, e.g., loss correction and label correction, cannot handle such open-set noisy…

High-risk artificial intelligence and machine learning classification tasks, such as healthcare diagnosis, require accurate and interpretable prediction models. However, classifier algorithms typically sacrifice individual case-accuracy for…

Data assimilation refers to the problem of finding trajectories of a prescribed dynamical model in such a way that the output of the model (usually some function of the model states) follows a given time series of observations. Typically…

Failure of machine learning models to generalize to new data is a core problem limiting the reliability of AI systems, partly due to the lack of simple and robust methods for comparing new data to the original training dataset. We propose a…

Zero-shot learning (ZSL) endows the computer vision system with the inferential capability to recognize instances of a new category that has never seen before. Two fundamental challenges in it are visual-semantic embedding and domain…

In policy learning for robotic manipulation, sample efficiency is of paramount importance. Thus, learning and extracting more compact representations from camera observations is a promising avenue. However, current methods often assume full…

AI-driven decision-making systems are becoming instrumental in the public sector, with applications spanning areas like criminal justice, social welfare, financial fraud detection, and public health. While these systems offer great…

Data stream mining problem has caused widely concerns in the area of machine learning and data mining. In some recent studies, ensemble classification has been widely used in concept drift detection, however, most of them regard…

Current vision-guided audio captioning systems frequently fail to address audiovisual misalignment in real-world scenarios, such as dubbed content or off-screen sounds. To bridge this critical gap, we present an entropy-aware gated fusion…

Uncorrelated optical space observation association represents a classic needle in a haystack problem. The objective being to find small groups of observations that are likely of the same resident space objects (RSOs) from amongst the much…

Sample selection is a prevalent method in learning with noisy labels, where small-loss data are typically considered as correctly labeled data. However, this method may not effectively identify clean hard examples with large losses, which…

In the last few years we have seen a growing interest in machine learning approaches to computer vision and, especially, to semantic labeling. Nowadays state of the art systems use deep learning on millions of labeled images with very…

Intelligent tutoring systems increasingly provide automated feedback on student work, but robust feedback requires assessing reasoning, not only final answers. We study a failure mode we call the correct answer trap (CAT): models…

Early supervised machine learning algorithms have relied on reliable expert labels to build predictive models. However, the gates of data generation have recently been opened to a wider base of users who started participating increasingly…

Machine Unlearning (MU) aims to remove target training data from a trained model so that the removed data no longer influences the model's behavior, fulfilling "right to be forgotten" obligations under data privacy laws. Yet, we observe…

Intersectional bias is a bias caused by an overlap of multiple social factors like gender, sexuality, race, disability, religion, etc. A recent study has shown that word embedding models can be laden with biases against intersectional…

An implicit association test is a human psychological test used to measure subconscious associations. While widely recognized by psychologists as an effective tool in measuring attitudes and biases, the validity of the results can be…

Access to obstetric ultrasound is often limited in low-resource settings, particularly in rural areas of low- and middle-income countries. This work proposes a human-in-the-loop artificial intelligence (AI) system designed to assist…

Understanding and explaining the mistakes made by trained models is critical to many machine learning objectives, such as improving robustness, addressing concept drift, and mitigating biases. However, this is often an ad hoc process that…

We introduce an adaptive method with formal quality guarantees for weak supervision in a non-stationary setting. Our goal is to infer the unknown labels of a sequence of data by using weak supervision sources that provide independent noisy…