Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022
Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022
Li Gu Zhixiang Chi Huan Liu Yuanhao Yu Yang Wang

Abstract
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.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| few-shot-image-classification-on-orbit | ProtoNetsVideo | Frame accuracy: 71.69 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.