activity
20212023
most citedProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning

1 citations · 2 across the 4 of their papers we have counts for

collaborators
Showing 2022Show all

1 paper · 1 filter

cs.CV2022

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…