Data hungry – Un/Semi/Weakly-supervised learning

This biases vision researchers to work on tasks where annotation is easy instead of tasks that are important

Generalization issue – Sensor/Environment changes

Deep Nets perform well on benchmark datasets, but can fail badly on real-world images outside the dataset

Efficient learning – Multi-task Learning, Dynamic Neural Net

Real-world applications require efficient neural networks for multiple tasks to run simultaneously

Robustness issues – Neural net layer design

Deep Nets are overly sensitive to changes in the image which would not fool a human observer