Dense open-set recognition based on training with noisy negative images

Petra Bevandic, Ivan Kreso, Marin Orsic, Sinisa Segvic

Abstract: Highlights•Training with noisy negative images greatly improves dense open-set recognition.•Training with randomly pasted negatives improves generalization on mixed-content images.•Shared features improve outlier detection and allow for inference with a single forward pass.•State-of-the-art results on dense open-set recognition benchmarks: WildDash 1, Fishyscapes and StreetHazard.