Any-Shot Object Detection

Understand

Previous work on novel object detection considers zero or few-shot settings where none or few examples of each category are available for training.

• In real world scenarios, it is less practical to expect that 'all' the novel classes are either unseen or {have} few-examples.
• Here, we propose a more realistic setting termed 'Any-shot detection', where totally unseen and few-shot categories can simultaneously co-occur during inference.
• Any-shot detection offers unique challenges compared to conventional novel object detection such as, a high imbalance between unseen, few-shot and seen object classes, susceptibility to forget base-training while learning novel classes and distinguishing novel classes from the background.