In recent years, online distillation has emerged as a powerful technique for adapting real-time deep neural networks on the fly using a slow, but accurate teacher model. However, a major challenge in online distillation is catastrophic forgetting when the domain shifts, which occurs when the student model is updated with data from the new domain and forgets previously learned knowledge. In this paper, we propose a solution to this issue by leveraging the power of continual learning methods to reduce the impact of domain shifts. Specifically, we integrate several state-of-the-art continual learning methods in the context of online distillation and demonstrate their effectiveness in reducing catastrophic forgetting. Furthermore, we provide a detailed analysis of our proposed solution in the case of cyclic domain shifts. Our experimental results demonstrate the efficacy of our approach in improving the robustness and accuracy of online distillation, with potential applications in domains such as video surveillance or autonomous driving. Overall, our work represents an important step forward in the field of online distillation and continual learning, with the potential to significantly impact real-world applications.
|Original language||English (US)|
|Title of host publication||Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023|
|Publisher||IEEE Computer Society|
|Number of pages||10|
|State||Published - 2023|
|Event||2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 - Vancouver, Canada|
Duration: Jun 18 2023 → Jun 22 2023
|Name||IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops|
|Conference||2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023|
|Period||06/18/23 → 06/22/23|
Bibliographical notePublisher Copyright:
© 2023 IEEE.
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering