Yan Luo

Foveation-based Mechanisms Alleviate Adversarial Examples

2015 · arXiv (Cornell University)

We show that adversarial examples, i.e., the visually imperceptible perturbations that result in Convolutional Neural Networks (CNNs) fail, can be alleviated with a mechanism based on foveations---applying the CNN in different image regions. To see …

Multi-attribute Collaborative Filtering Recommendation

2015

Currently researchers in the field of personalized recommendations bear little consideration on users' interest differences in resource attributes although re- source attribute is usually one of the most important factors in determining user pref- erences. …

Toward Secure, Privacy-Preserving, and Interoperable Medical Data Sharing via Blockchain

2019

In the era of cloud computing and big data analysis, how to efficiently share and utilize medical information scattered across various care providers has become a critical problem. This paper proposes a new framework for …

Learning to Predict Trustworthiness with Steep Slope Loss

2021 · arXiv (Cornell University)

Understanding the trustworthiness of a prediction yielded by a classifier is critical for the safe and effective use of AI models. Prior efforts have been proven to be reliable on small-scale datasets. In this work, …

Three-dimensional visualization of thyroid ultrasound images based on multi-scale features fusion and hierarchical attention

2024 · BioMedical Engineering OnLine

BACKGROUND: Ultrasound three-dimensional visualization, a cutting-edge technology in medical imaging, enhances diagnostic accuracy by providing a more comprehensive and readable portrayal of anatomical structures compared to traditional two-dimensional ultrasound. Crucial to this visualization is the …

Interpretability in Sentiment Analysis: A Self-Supervised Approach to Sentiment Cue Extraction

2024 · Applied Sciences

In this paper, we present a novel self-supervised framework for Sentiment Cue Extraction (SCE) aimed at enhancing the interpretability of text sentiment analysis models. Our approach leverages self-supervised learning to identify and highlight key textual …