mlsanityData to 7 Oct 2026

Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022

arXiv 2210.00174 ↗First posted 1 Oct 2022cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 17 of its 22 references that are in the map. First posted on arXiv 1 Oct 2022.

Builds on

17 of 22 references.

References · 17

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2016Matching Networks for One Shot Learningcited by 2,246
  5. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  6. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  7. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  8. 2020Few-Shot Class-Incremental Learningcited by 249
  9. 2020Adaptive Risk Minimization: Learning to Adapt to Domain Shiftcited by 183
  10. 2019Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processescited by 131
  11. 2022Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replaycited by 70
  12. 2022Bidirectional Learning for Offline Infinite-width Model-based Optimizationcited by 35
5 more
  1. 2021Test-Time Personalization with a Transformer for Human Pose Estimationcited by 33
  2. 2021ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognitioncited by 29
  3. 2022Gradient-based Bi-level Optimization for Deep Learning: A Surveycited by 26
  4. 2021Self-supervised Spatiotemporal Representation Learning by Exploiting Video Continuitycited by 22
  5. 2021Memory Efficient Meta-Learning with Large Imagescited by 14

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 3.

5 papers.

  1. 2022Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Expertscited by 50
  2. 2023MetaGCD: Learning to Continually Learn in Generalized Category Discoverycited by 40
  3. 2025Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptationcited by 14
  4. 2025DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learningcited by 3
  5. 2025MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuningcited by 2