Just Label What You Need: Fine-Grained Active Selection for Perception and Prediction through Partially Labeled Scenes
This addresses the high labeling costs in self-driving data for companies and researchers, offering an incremental improvement over existing active learning methods.
The paper tackles the problem of selecting which examples to label for training perception and prediction models in self-driving vehicles, finding that traditional active learning is ill-suited and introducing a cost-aware, fine-grained approach that improves performance across tasks.
Self-driving vehicles must perceive and predict the future positions of nearby actors in order to avoid collisions and drive safely. A learned deep learning module is often responsible for this task, requiring large-scale, high-quality training datasets. As data collection is often significantly cheaper than labeling in this domain, the decision of which subset of examples to label can have a profound impact on model performance. Active learning techniques, which leverage the state of the current model to iteratively select examples for labeling, offer a promising solution to this problem. However, despite the appeal of this approach, there has been little scientific analysis of active learning approaches for the perception and prediction (P&P) problem. In this work, we study active learning techniques for P&P and find that the traditional active learning formulation is ill-suited for the P&P setting. We thus introduce generalizations that ensure that our approach is both cost-aware and allows for fine-grained selection of examples through partially labeled scenes. Our experiments on a real-world, large-scale self-driving dataset suggest that fine-grained selection can improve the performance across perception, prediction, and downstream planning tasks.