6 papers
PrefPaint: Enhancing Medical Image Inpainting through Expert Human Feedback
Duy-Bao Bui, Hoang-Khang Nguyen, Thao Thi Phuong Dao +5
Inpainting, the process of filling missing or corrupted image parts, has broad applications in medical imaging. However, generating anatomically accurate synthetic polyp images for…
Efficient Domain Adaptation for Text Line Recognition via Decoupled Language Models
Arundhathi Dev, Justin Zhan
Optical character recognition remains critical infrastructure for document digitization, yet state-of-the-art performance is often restricted to well-resourced institutions by proh…
Domain-Generalization to Improve Learning in Meta-Learning Algorithms
Usman Anjum, Chris Stockman, Cat Luong +1
This paper introduces Domain Generalization Sharpness-Aware Minimization Model-Agnostic Meta-Learning (DGS-MAML), a novel meta-learning algorithm designed to generalize across task…
Fine-tuning BERT with Bidirectional LSTM for Fine-grained Movie Reviews Sentiment Analysis
Gibson Nkhata, Susan Gauch, Usman Anjum +1
Sentiment Analysis (SA) is instrumental in understanding peoples viewpoints facilitating social media monitoring recognizing products and brands and gauging customer satisfaction.…
Sentiment Analysis of Movie Reviews Using BERT
Gibson Nkhata, Usman Anjum, Justin Zhan
Sentiment Analysis (SA) or opinion mining is analysis of emotions and opinions from any kind of text. SA helps in tracking peoples viewpoints and it is an important factor when it…
Towards Modeling Data Quality and Machine Learning Model Performance
Usman Anjum, Chris Trentman, Elrod Caden +1
Understanding the effect of uncertainty and noise in data on machine learning models (MLM) is crucial in developing trust and measuring performance. In this paper, a new model is p…