Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
This work addresses robustness issues in object detectors for safety-critical applications like autonomous driving, though it is incremental as it builds on existing testing methods.
The authors tackled the problem of unreliable uncertainty quantification and calibration in object detectors, introducing the Self-Aware Object Detection (SAOD) task as a unified testing framework with novel metrics and large-scale datasets, and provided a simple baseline for benchmarking.
The current approach for testing the robustness of object detectors suffers from serious deficiencies such as improper methods of performing out-of-distribution detection and using calibration metrics which do not consider both localisation and classification quality. In this work, we address these issues, and introduce the Self-Aware Object Detection (SAOD) task, a unified testing framework which respects and adheres to the challenges that object detectors face in safety-critical environments such as autonomous driving. Specifically, the SAOD task requires an object detector to be: robust to domain shift; obtain reliable uncertainty estimates for the entire scene; and provide calibrated confidence scores for the detections. We extensively use our framework, which introduces novel metrics and large scale test datasets, to test numerous object detectors in two different use-cases, allowing us to highlight critical insights into their robustness performance. Finally, we introduce a simple baseline for the SAOD task, enabling researchers to benchmark future proposed methods and move towards robust object detectors which are fit for purpose. Code is available at https://github.com/fiveai/saod