Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022
2022-10-01Code Available1· sign in to hype
Li Gu, Zhixiang Chi, Huan Liu, Yuanhao Yu, Yang Wang
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/guliisgreat/orbit-2022-winner-methodOfficialIn paperpytorch★ 15
- github.com/2023-MindSpore-1/ms-code-215/tree/main/ProtoNetmindspore★ 0
- github.com/code-implementation1/Code6/tree/main/ProtoNetmindspore★ 0
- github.com/MindSpore-paper-code-2/code2/tree/main/ProtoNetmindspore★ 0
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| ORBIT Clutter Video Evaluation | ProtoNetsVideo | Frame accuracy | 71.69 | — | Unverified |