1 citations · 2 across the 4 of their papers we have counts for
4 papers
ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning
Islam Nassar, Munawar Hayat, Ehsan Abbasnejad +2
Confidence-based pseudo-labeling is among the dominant approaches in semi-supervised learning (SSL). It relies on including high-confidence predictions made on unlabeled data as ad…
LAVA: Label-efficient Visual Learning and Adaptation
Islam Nassar, Munawar Hayat, Ehsan Abbasnejad +3
We present LAVA, a simple yet effective method for multi-domain visual transfer learning with limited data. LAVA builds on a few recent innovations to enable adapting to partially…
Generate, Annotate, and Learn: NLP with Synthetic Text
Xuanli He, Islam Nassar, Jamie Kiros +2
This paper studies the use of language models as a source of synthetic unlabeled text for NLP. We formulate a general framework called ``generate, annotate, and learn (GAL)'' to ta…
All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training
Islam Nassar, Samitha Herath, Ehsan Abbasnejad +2
Pseudo-labeling is a key component in semi-supervised learning (SSL). It relies on iteratively using the model to generate artificial labels for the unlabeled data to train against…