Tag: label uncertainty

CLASSIFICATION WITH MULTI-IMPRECISE LABELS

Abstract: Imprecise labels or label uncertainty are common problems in many real supervised and semi-supervised learning problems. However, most of the state-of-the-art supervised learning methods in the literature rely on accurate labels. Accurate labels are often either expensive, time-consuming, or… Read More

WEAKLY-LABELED RAND INDEX ACCEPTED TO IGARSS!

Congratulations to our labmates: Dylan Stewart, Anna Hampton, Alina Zare, Jeff Dale and James Keller!  Their paper, “The Weakly-Labeled Rand Index” was recently accepted to the IEEE International Geoscience and Remote Sensing Symposium (IGARSS). In their paper, the authors introduce… Read More

THE WEAKLY-LABELED RAND INDEX

Abstract: Synthetic Aperture Sonar (SAS) surveys produce imagery with large regions of transition between seabed types. Due to these regions, it is difficult to label and segment the imagery and, furthermore, challenging to score the image segmentations appropriately. While there… Read More

ROOT IDENTIFICATION WITH MULTIPLE INSTANCE LEARNING PUBLISHED IN MACHINE VISION AND APPLICATIONS!

Congratulations to our labmates and collaborators Guohao Yu, Alina Zare, Hudanyun Sheng, Roser Matamala, Joel Reyes-Cabrera, Felix Fritschi and Thomas Juenger! Their paper, “Root Identification in Minirhizotron Imagery with Multiple Instance Learning”, was recently published in Machine Vision and Applications!… Read More

ROOT IDENTIFICATION WITH MULTIPLE INSTANCE LEARNING ACCEPTED TO MACHINE VISION AND APPLICATIONS!

Congratulations to our labmates Guohao Yu, Alina Zare and Hudanyun Sheng, as well as collaborators, Roser Matamala, Joel Reyes-Cabrera, Felix Fritschi and Thomas Juenger! Their paper, “Root Identification in Minirhizotron Imagery with Multiple Instance Learning”, was recently accepted to Machine… Read More

Multi-Resolution Multi-Modal Sensor Fusion For Remote Sensing Data With Label Uncertainty

Abstract: In remote sensing, each sensor can provide complementary or reinforcing information. It is valuable to fuse outputs from multiple sensors to boost overall performance. Previous supervised fusion methods often require accurate labels for each pixel in the training data.… Read More