Jose Oramas M

University of Antwerp, Computer Science, Faculty Member

Followers

Following

Co-authors

Public Views

I am a post-doctoral researcher at the KU Leuven, where I received my Ph.D. in 2015 under the advice of Prof. Tinne Tuytelaars and Prof. Luc de Raedt. I received a Computer Engineering degree from the Escuela Superior Politécnica del Litoral, Ecuador. My research focuses on understanding how groups of elements within images (objects, object-parts,regions, trajectories, etc.) behave and how the relations between them can be exploited to address computer vision problems.

My research interests include: Context-Aware Reasoning, Collective Classification, Relational Learning, Scene Understanding, Sign Language/Gesture Recognition.

less

Steven Pinker

Harvard University

Armando Marques-Guedes

UNL - New University of Lisbon

Fabio Cuzzolin

Oxford Brookes University

Lev Manovich

Graduate Center of the City University of New York

Isad Saric

University of Sarajevo

Bogdan Gabrys

University of Technology Sydney

PALIMOTE JUSTICE

RIVERS STATE POLYTECHNIC

mahmoud hafiz

Al-Azhar University

Bálint Molnár

Eötvös Loránd University

Ferhat Bozkurt

Ataturk University

InterestsView All (11)

Uploads

Papers by Jose Oramas M

Object Detection with Semi-supervised Adversarial Domain Adaptation for Real-Time Edge Devices

Springer eBooks, 2022

FICNN: A Framework for the Interpretation of Deep Convolutional Neural Networks

arXiv (Cornell University), May 17, 2023

With the continue development of Convolutional Neural Networks (CNNs), there is a growing concern... more With the continue development of Convolutional Neural Networks (CNNs), there is a growing concern regarding representations that they encode internally. Analyzing these internal representations is referred to as model interpretation. While the task of model explanation, justifying the predictions of such models, has been studied extensively; the task of model interpretation has received less attention. The aim of this paper is to propose a framework for the study of interpretation methods designed for CNN models trained from visual data. More specifically, we first specify the difference between the interpretation and explanation tasks which are often considered the same in the literature. Then, we define a set of six specific factors that can be used to characterize interpretation methods. Third, based on the previous factors, we propose a framework for the positioning of interpretation methods. Our framework highlights that just a very small amount of the suggested factors, and combinations thereof, have been actually studied. Consequently, leaving significant areas unexplored. Following the proposed framework, we discuss existing interpretation methods and give some attention to the evaluation protocols followed to validate them. Finally, the paper highlights capabilities of the methods in producing feedback for enabling interpretation and proposes possible research problems arising from the framework.

Jose Oramas M

Uploads

Papers by Jose Oramas M

Log In