SOP^2: Transfer Learning with Scene-Oriented Prompt Pool on 3D Object Detection
This work addresses the challenge of efficient transfer learning for 3D object detection, which is incremental as it applies existing prompt tuning concepts to a new domain.
The paper tackles the problem of adapting prompt tuning methods from NLP to 3D object detection, proposing a Scene-Oriented Prompt Pool (SOP^2) and demonstrating its effectiveness in transferring a model trained on the Waymo dataset to other scenarios.
With the rise of Large Language Models (LLMs) such as GPT-3, these models exhibit strong generalization capabilities. Through transfer learning techniques such as fine-tuning and prompt tuning, they can be adapted to various downstream tasks with minimal parameter adjustments. This approach is particularly common in the field of Natural Language Processing (NLP). This paper aims to explore the effectiveness of common prompt tuning methods in 3D object detection. We investigate whether a model trained on the large-scale Waymo dataset can serve as a foundation model and adapt to other scenarios within the 3D object detection field. This paper sequentially examines the impact of prompt tokens and prompt generators, and further proposes a Scene-Oriented Prompt Pool (\textbf{SOP$^2$}). We demonstrate the effectiveness of prompt pools in 3D object detection, with the goal of inspiring future researchers to delve deeper into the potential of prompts in the 3D field.