COCO-TEACH: A Contrastive Co-Teaching Network For Incremental 3D Object Detection

Page view(s)
59
Checked on Dec 12, 2024
COCO-TEACH: A Contrastive Co-Teaching Network For Incremental 3D Object Detection
Title:
COCO-TEACH: A Contrastive Co-Teaching Network For Incremental 3D Object Detection
Journal Title:
2023 IEEE International Conference on Image Processing (ICIP)
Keywords:
Publication Date:
11 September 2023
Citation:
Cheng, Z., Chen, C., Zhao, Z., Qian, P., Li, X., & Yang, X. (2023). COCO-TEACH: A Contrastive Co-Teaching Network For Incremental 3D Object Detection. 2023 IEEE International Conference on Image Processing (ICIP). https://doi.org/10.1109/icip49359.2023.10222538
Abstract:
Deep learning (DL) models for 3D object detection from point clouds have shown remarkable progress in various autonomous perception scenarios. However, the issue of catastrophic forgetting seriously hinders the deployment of these models in real-world applications where new classes are encountered over time. In order to address this issue, we present the Contrastive Co-Teaching Network (COCO- TEACH) framework for class-incremental 3D object de- tection. Our proposed framework consists of two teacher networks: a primary teacher network that detects old class objects in new data and provides them with pseudo-labels and an auxiliary teacher network that leverages the unla- belled objects in new data. The two teacher models transfer their learned knowledge to the target student model through a class-aware consistency loss. To enhance this transfer, a supervised contrastive loss is further incorporated into the loss function. We evaluate the performance of our proposed method against baseline methods through extensive experi- ments on two benchmark datasets. The results show that our proposed framework achieves state-of-the-art performance on incremental 3D object detection
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation - AI Singapore Programme
Grant Reference no. : AISG2-RP-2021-027
Description:
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISBN:
978-1-7281-9835-4
Files uploaded:

File Size Format Action
icip2023-coco-teach.pdf 320.14 KB PDF Request a copy