Search Results for author:
Found 6 papers, 3 papers with code
Trans-Caps: Transformer Capsule Networks with Self-attention Routing
Capsule Networks (CapsNets) have shown to be a promising alternative to Convolutional Neural Networks (CNNs) in many computer vision tasks, due to their ability to encode object viewpoint variations.
Polaratio: A magnitude-contingent monotonic correlation metric and its improvements to scRNA-seq clustering
Results: We integrate three state-of-the-art interpretable clustering algorithms – Single-Cell Consensus Clustering (SC3), Hierarchical Clustering (HC), and K-Medoids (KM) – through a consensus cell clustering procedure, which we evaluate on various biological datasets to benchmark Polaratio against several well-known metrics.
Ranked #1 on
Graph Clustering
on Biase et al
StyPath: Style-Transfer Data Augmentation For Robust Histology Image Classification
We also generated Grad-CAM representations of the results which were assessed by an experienced nephropathologist; we used this qualitative analysis to elucidate on the assumptions being made by each model.
Few Is Enough: Task-Augmented Active Meta-Learning for Brain Cell Classification
Meta-learning aims to deliver an adaptive model that is sensitive to these underlying distribution changes, but requires many tasks during the meta-training process.
DECAPS: Detail-Oriented Capsule Networks
We provide extensive experiments on the CheXpert and RSNA Pneumonia datasets to validate the effectiveness of DECAPS.
Radiologist-Level COVID-19 Detection Using CT Scans with Detail-Oriented Capsule Networks
The network then uses the activation maps to focus on regions of interest and combines both coarse and fine-grained representations of the data.
