Towards PAC Multi-Object Detection and Tracking
This work addresses the need for reliable performance assurances in autonomous navigation and similar domains, representing an incremental advancement by applying conformal prediction to a new task.
The paper tackles the challenge of providing performance guarantees for multi-object detection and tracking in safety-critical applications by proposing algorithms with probably approximately correct (PAC) guarantees, empirically demonstrating their effectiveness on COCO and MOT-17 datasets.
Accurately detecting and tracking multi-objects is important for safety-critical applications such as autonomous navigation. However, it remains challenging to provide guarantees on the performance of state-of-the-art techniques based on deep learning. We consider a strategy known as conformal prediction, which predicts sets of labels instead of a single label; in the classification and regression settings, these algorithms can guarantee that the true label lies within the prediction set with high probability. Building on these ideas, we propose multi-object detection and tracking algorithms that come with probably approximately correct (PAC) guarantees. They do so by constructing both a prediction set around each object detection as well as around the set of edge transitions; given an object, the detection prediction set contains its true bounding box with high probability, and the edge prediction set contains its true transition across frames with high probability. We empirically demonstrate that our method can detect and track objects with PAC guarantees on the COCO and MOT-17 datasets.