MetaFusion: Controlled False-Negative Reduction of Minority Classes in Semantic Segmentation
This addresses safety-critical applications like autonomous driving by reducing overlooked pedestrians, though it is incremental as it builds on existing methods for false-positive detection.
The paper tackled the problem of underrepresented classes in semantic segmentation, such as pedestrians in street scenes, by combining decision rules with false-positive detection to reduce false-negatives without significantly increasing false-positives, achieving improved trade-offs on the Cityscapes dataset.
In semantic segmentation datasets, classes of high importance are oftentimes underrepresented, e.g., humans in street scenes. Neural networks are usually trained to reduce the overall number of errors, attaching identical loss to errors of all kinds. However, this is not necessarily aligned with human intuition. For instance, an overlooked pedestrian seems more severe than an incorrectly detected one. One possible remedy is to deploy different decision rules by introducing class priors which assigns larger weight to underrepresented classes. While reducing the false-negatives of the underrepresented class, at the same time this leads to a considerable increase of false-positive indications. In this work, we combine decision rules with methods for false-positive detection. We therefore fuse false-negative detection with uncertainty based false-positive meta classification. We present proof-of-concept results for CIFAR-10, and prove the efficiency of our method for the semantic segmentation of street scenes on the Cityscapes dataset based on predicted instances of the 'human' class. In the latter we employ an advanced false-positive detection method using uncertainty measures aggregated over instances. We thereby achieve improved trade-offs between false-negative and false-positive samples of the underrepresented classes.