Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022
This work addresses few-shot video object recognition for computer vision researchers, but it is incremental as it builds on the existing ProtoNet baseline.
The paper tackled few-shot video object recognition by enhancing ProtoNet with three techniques—embedding adaptation, uniform video clip sampling, and invalid frame detection—and won the ORBIT Challenge 2022, achieving improved performance through codebase optimization and faster data loading.
In this work, we present the winning solution for ORBIT Few-Shot Video Object Recognition Challenge 2022. Built upon the ProtoNet baseline, the performance of our method is improved with three effective techniques. These techniques include the embedding adaptation, the uniform video clip sampler and the invalid frame detection. In addition, we re-factor and re-implement the official codebase to encourage modularity, compatibility and improved performance. Our implementation accelerates the data loading in both training and testing.