False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates
This work addresses the safety-critical issue of missed detections in automated driving by providing a post-processing solution to reduce false negatives, though it is incremental as it builds on existing instance segmentation networks.
The paper tackles the problem of false negatives in video instance segmentation, which is critical for safety-sensitive applications like automated driving, by introducing a post-processing method that uses uncertainty estimates and temporal inconsistencies to reduce false negatives while pruning false positives, achieving an improved trade-off between false negative and false positive instances compared to standard score-based approaches.
Instance segmentation of images is an important tool for automated scene understanding. Neural networks are usually trained to optimize their overall performance in terms of accuracy. Meanwhile, in applications such as automated driving, an overlooked pedestrian seems more harmful than a falsely detected one. In this work, we present a false negative detection method for image sequences based on inconsistencies in time series of tracked instances given the availability of image sequences in online applications. As the number of instances can be greatly increased by this algorithm, we apply a false positive pruning using uncertainty estimates aggregated over instances. To this end, instance-wise metrics are constructed which characterize uncertainty and geometry of a given instance or are predicated on depth estimation. The proposed method serves as a post-processing step applicable to any neural network that can also be trained on single frames only. In our tests, we obtain an improved trade-off between false negative and false positive instances by our fused detection approach in comparison to the use of an ordinary score value provided by the instance segmentation network during inference.