Do You Remember the Future? Weak-to-Strong Generalization in 3D Object Detection
Do You Remember the Future? Weak-to-Strong Generalization in 3D Object Detection
Alexander Gambashidze, Aleksandr Dadukin, Maxim Golyadkin, Maria Razzhivina, Ilya Makarov
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Demo Track. Pages 8653-8656.
https://doi.org/10.24963/ijcai.2024/1001
This paper demonstrates a novel method for LiDAR-based 3D object detection, addressing major field challenges: sparsity and occlusion. Our approach leverages temporal point cloud sequences to generate frames that provide comprehensive views of objects from multiple angles. To address the challenge of generating these frames in real-time, we employ Knowledge Distillation within a Teacher-Student framework, allowing the Student model to emulate the Teacher’s advanced perception. We pioneered the application of weak-to-strong generalization in computer vision by training our Teacher model on enriched, object-complete data. In this demo, we showcase the exceptional quality of labels produced by the X-Ray Teacher on object-complete frames, showing our method distilling its knowledge to enhance object 3D detection models.
Keywords:
Computer Vision: CV: 3D computer vision
Computer Vision: CV: Recognition (object detection, categorization)