Task Regularized Hybrid Knowledge Distillation For Continual Object Detection

Jinming Zhang, Mengxue Kang, Jinpeng Zhang, Zhe Ma, Shan Yu

Keywords: Knowledge Distillation, Continual Learning, Continual Object Detection, Class Incremental Object Detection

TL;DR: Task Regularized Hybrid Knowledge Distillation Method For Class Incremental Objects Detection

Abstract: Knowledge distillation has been used to overcome catastrophic forgetting in Continual Object Detection(COD) task. Previous works mainly focus on combining different distillation methods, including feature, classification, location and relation, into a mixed scheme to solve this problem. In this paper, we propose a task regularized hybrid knowledge distillation method for COD task. First, we propose an image-level hybrid knowledge representation by combining instance-level hard and soft knowledge to use teacher knowledge critically. Second, we propose a task-based regularization distillation loss by taking account of loss and category differences to make continual learning more balance between old and new tasks. We find that, under appropriate knowledge selection and transfer strategies, using only classification distillation can also relieve knowledge forgetting effectively. Extensive experiments conducted on MS COCO2017 demonstrate that our method achieves state-of-the-art results under various scenarios. We get an absolute improvement of 27.98 at $RelGap$ under the most difficult five-task scenario. Code is in attachment and will be available on github.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning