Uni$^2$Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection

TL;DR

Uni$^2$Det is a novel framework that enables unified multi-dataset training for 3D detection, effectively handling dataset disparities and generalizing well to unseen domains, with strong empirical results across multiple datasets.

Contribution

The paper introduces multi-stage prompting modules for 3D detection that unify diverse datasets and improve cross-domain generalization in a plug-and-play manner.

Findings

Outperforms existing methods in multi-dataset training scenarios.

Demonstrates strong zero-shot transfer capabilities.

Effective across datasets like KITTI, Waymo, and nuScenes.

Abstract

We present Uni$^2$Det, a brand new framework for unified and universal multi-dataset training on 3D detection, enabling robust performance across diverse domains and generalization to unseen domains. Due to substantial disparities in data distribution and variations in taxonomy across diverse domains, training such a detector by simply merging datasets poses a significant challenge. Motivated by this observation, we introduce multi-stage prompting modules for multi-dataset 3D detection, which leverages prompts based on the characteristics of corresponding datasets to mitigate existing differences. This elegant design facilitates seamless plug-and-play integration within various advanced 3D detection frameworks in a unified manner, while also allowing straightforward adaptation for universal applicability across datasets. Experiments are conducted across multiple dataset consolidation scenarios involving KITTI, Waymo, and nuScenes, demonstrating that our Uni$^2$Det outperforms existing methods by a large margin in multi-dataset training. Notably, results on zero-shot cross-dataset transfer validate the generalization capability of our proposed method.