Simplicity bias is the concerning tendency of deep networks to over-depe...
Concept bottleneck models (CBMs) (Koh et al. 2020) are interpretable neu...
Object trackers deployed on low-power devices need to be light-weight,
h...
Gradient based meta-learning methods are prone to overfit on the
meta-tr...
Continual learning (CL) aims to develop techniques by which a single mod...
Structured pruning methods are among the effective strategies for extrac...
Deeper and wider CNNs are known to provide improved performance for deep...
Endoscopic artefact detection challenge consists of 1) Artefact detectio...