Person
Ksenia Konyushkova
This person is no longer with EPFL
Related publications (5)
Learning to Reduce Annotation Load
Modern machine learning methods and their applications in computer vision are known to crave for large amounts of training data to reach their full potential. Because training data is mostly obtained through humans who manually label samples, it induces a ...
EPFL2019Geometry in active learning for binary and multi-class image segmentation
Pascal Fua, Raphael Sznitman, Ksenia Konyushkova
We propose an active learning approach to image segmentation that exploits geometric priors to speed up and streamline the annotation process. It can be applied for both background foreground and multi-class segmentation tasks in 2D images and 3D image vol ...
2019Learning Intelligent Dialogs for Bounding Box Annotation
Ksenia Konyushkova, Vittorio Ferrari
We introduce Intelligent Annotation Dialogs for bounding box annotation. We train an agent to automatically choose a sequence of actions for a human annotator to produce a bounding box in a minimal amount of time. Specifically, we consider two actions: box ...
IEEE2018Learning Active Learning from Data
Pascal Fua, Raphael Sznitman, Ksenia Konyushkova
In this paper, we suggest a novel data-driven approach to active learning (AL). The key idea is to train a regressor that predicts the expected error reduction for a candidate sample in a particular learning state. By formulating the query selection proced ...
2017Introducing Geometry in Active Learning for Image Segmentation
Pascal Fua, Raphael Sznitman, Ksenia Konyushkova
We propose an Active Learning approach to training a segmentation classifier that exploits geometric priors to streamline the annotation process in 3D image volumes. To this end, we use these priors not only to select voxels most in need of annotation but ...
2015