Abstract: Open-set classification of small targets in high-resolution maritime radars is a difficult problem. Due to various small targets, classifiers in service always encounter samples from unknown ...
Existing remote-sensing scene image (RSSI) classification methods usually rely on the static closed-set assumption that testing samples do not belong to unknown classes. However, practical ...
OpenLoss: This repository discloses cost functions designed for open-set classification tasks, namely, Entropic Open-set, ObjectoSphere and Maximal-Entropy Loss. OpenLoss: This repository discloses ...
Official Implementation of "Domain Adaptive Few-Shot Open-Set Learning" in IEEE/CVF International Conference on Computer Vision (ICCV'23) OpenLoss: This repository discloses cost functions designed ...