Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection
By Na Zhao, Gim Hee Lee. 2021
27 citations recorded by the source corpus.
Deep learning-based approaches have shown remarkable performance in the 3D object detection task. However, they suffer from a catastrophic performance drop on the originally trained classes when incrementally learning new classes without revisiting the old data. This "catastrophic forgetting" phenomenon impedes the deployment of 3D object detection approaches in real-world scenarios, where continuous learning systems are needed. In this paper, we study the unexplored yet important class-incremental 3D object detection problem and present the first solution - SDCoT, a novel static-dynamic co-teaching method. Our SDCoT alleviates the catastrophic forgetting of old classes via a static teacher, which provides pseudo annotations for old classes in the new samples and regularizes the current model by extracting previous knowledge with a distillation loss. At the same time, SDCoT consistently learns the underlying knowledge from new data via a dynamic teacher. We conduct extensive experiments on two benchmark datasets and demonstrate the superior performance of our SDCoT over baseline approaches in several incremental learning scenarios. Our code is available at https://github.com/Na-Z/SDCoT.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 3D Vision & Pose, Meta & Continual Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
In 3D Vision & Pose
In Meta & Continual Learning
Citations in the corpus
- A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “IOD is not only applicable for 2D images, but also for 3D images [503] and videos [425].”
- Class-Incremental Learning: A Survey (2023, background): “Other recent works also address the specific settings like few-shot IOD [242], [270], [271], [272], open-world IOD [244] and 3D IOD [273].”