Hybrid Open-Set Segmentation With Synthetic Negative Data.

Open-set segmentation can be conceived by complementing closed-set classification with anomaly detection. Many of the existing dense anomaly detectors operate through generative modelling of regular data or by discriminating with respect to negative data. These two approaches optimize different objectives and therefore exhibit different failure modes.

Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data.

Standard machine learning is unable to accommodate inputs which do not belong to the training distribution. The resulting models often give rise to confident incorrect predictions which may lead to devastating consequences. This problem is especially demanding in the context of dense prediction since input images may be only partially anomalous.

The Use of Pathotype Data for the Selection and Development of Barley Lines with Useful Resistance to Scald.

Resistance in barley to scald caused by is readily overcome as virulent pathotypes in the pathogen population are selectively favoured over less virulent pathotypes. Diverse sources of resistance amongst host accessions have been found upon screening a wide array of accessions from around the world. Deciding which of these is of greatest value, and which are different from each other, takes a much greater investment of time and effort.