Search Results for author:
Found 9 papers, 3 papers with code
Federated Learning Enables Big Data for Rare Cancer Boundary Detection
Although machine learning (ML) has shown promise in numerous domains, there are concerns about generalizability to out-of-sample data.
OPFython: A Python-Inspired Optimum-Path Forest Classifier
Machine learning techniques have been paramount throughout the last years, being applied in a wide range of tasks, such as classification, object recognition, person identification, and image segmentation.
Grabber: A tool to improve convergence in interactive image segmentation
Extensive experiments with robot users on two datasets show in both cases that Grabber can significantly improve convergence, with faster delineation, higher effectiveness, and less user effort.
FOMTrace: Interactive Video Segmentation By Image Graphs and Fuzzy Object Models
Common users have changed from mere consumers to active producers of multimedia data content.
Semi-Automatic Data Annotation guided by Feature Space Projection
Data annotation using visual inspection (supervision) of each training sample can be laborious.
Semi-supervised deep learning based on label propagation in a 2D embedded space
We present a loop in which a deep neural network (VGG-16) is trained from a set with more correctly labeled samples along iterations, created by using t-SNE to project the features of its last max-pooling layer into a 2D embedded space in which labels are propagated using the Optimum-Path Forest semi-supervised classifier.
Learning CNN filters from user-drawn image markers for coconut-tree image classification
We present a method that needs a minimal set of user-selected images to train the CNN's feature extractor, reducing the number of required images to train the fully connected layers.
Intestinal Parasites Classification Using Deep Belief Networks
Currently, approximately $4$ billion people are infected by intestinal parasites worldwide.
Linking data separation, visual separation, and classifier performance using pseudo-labeling by contrastive learning
Lacking supervised data is an issue while training deep neural networks (DNNs), mainly when considering medical and biological data where supervision is expensive.
