What's in the Black Box? The False Negative Mechanisms Inside Object Detectors
This work addresses the problem of false negatives in object detection for robotics applications, highlighting challenges in translating models from benchmarks to real-world use.
The paper identifies five false negative mechanisms in object detectors and introduces a framework to quantify them, showing that these mechanisms differ significantly between benchmark datasets and robotics scenarios, with implications for real-world deployment.
In object detection, false negatives arise when a detector fails to detect a target object. To understand why object detectors produce false negatives, we identify five 'false negative mechanisms', where each mechanism describes how a specific component inside the detector architecture failed. Focusing on two-stage and one-stage anchor-box object detector architectures, we introduce a framework for quantifying these false negative mechanisms. Using this framework, we investigate why Faster R-CNN and RetinaNet fail to detect objects in benchmark vision datasets and robotics datasets. We show that a detector's false negative mechanisms differ significantly between computer vision benchmark datasets and robotics deployment scenarios. This has implications for the translation of object detectors developed for benchmark datasets to robotics applications. Code is publicly available at https://github.com/csiro-robotics/fn_mechanisms