41 citations · 126 across the 31 of their papers we have counts for
6 papers · 1 filter
Cognitively Inspired Learning of Incremental Drifting Concepts
Mohammad Rostami, Aram Galstyan
Humans continually expand their learned knowledge to new domains and learn new concepts without any interference with past learned experiences. In contrast, machine learning models…
Detection and Continual Learning of Novel Face Presentation Attacks
Mohammad Rostami, Leonidas Spinoulas, Mohamed Hussein +2
Advances in deep learning, combined with availability of large datasets, have led to impressive improvements in face presentation attack detection research. However, state-of-the-a…
Domain Adaptation for Sentiment Analysis Using Increased Intraclass Separation
Mohammad Rostami, Aram Galstyan
Sentiment analysis is a costly yet necessary task for enterprises to study the opinions of their customers to improve their products and to determine optimal marketing strategies.…
Secure Domain Adaptation with Multiple Sources
Serban Stan, Mohammad Rostami
Multi-source unsupervised domain adaptation (MUDA) is a framework to address the challenge of annotated data scarcity in a target domain via transferring knowledge from multiple an…
Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning
Xisen Jin, Bill Yuchen Lin, Mohammad Rostami +1
The ability to continuously expand knowledge over time and utilize it to rapidly generalize to new tasks is a key feature of human linguistic intelligence. Existing models that pur…
Domain Adaptation for the Segmentation of Confidential Medical Images
Serban Stan, Mohammad Rostami
Convolutional neural networks (CNNs) have led to significant improvements in the semantic segmentation of images. When source and target datasets come from different modalities, CN…