Abstract Representation learning of pathology whole-slide images (WSIs) has been has
primarily relied on weak supervision with Multiple Instance Learning (MIL). However the …

Instead of searching the entire network directly, current NAS approaches increasingly
search for multiple relatively small cells to reduce search costs. A major challenge is to …

Abstract Multiple Instance Learning (MIL) is a crucial weakly supervised learning method
applied across various domains, eg, medical diagnosis based on whole slide images …

It is now possible to conduct large scale perturbation screens with complex readout
modalities, such as different molecular profiles or high content cell images. While these …

Data for pretraining machine learning models often consists of collections of heterogeneous
datasets. Although training on their union is reasonable in agnostic settings, it might be …

Learned visual representations often capture large amounts of semantic information for
accurate downstream applications. Human understanding of the world is fundamentally …

In the pursuit of robust autonomous driving systems, models trained on real-world datasets
often struggle to adapt to new environments, particularly when confronted with corner cases …

Optimal Transport (OT) is a fundamental tool for comparing probability distributions, but its
exact computation remains prohibitive for large datasets. In this work, we introduce novel …

This paper presents an improved harmony search algorithm (OP-HSA) for missing fault data
processing, to find a relatively optimal missing data imputation method from the alternatives …