|
March 11th, 2020
Daniela Lopez de Luise
|
March 11th, 2020
Daniela Lopez de Luise CLVISION CVPR 2020: Workshop on Continual Learning in Computer Vision
OVERVIEW
During the past few years we have witnessed a renewed and growing attention to Continuous Learning (CL). The interest in CL is essentially twofold. From the artificial intelligence perspective, CL can be seen as another important step towards the grand goal of creating autonomous agents which can learn continuously and acquire new and complex skills and knowledge. From a more practical perspective, CL looks particularly appealing because it enables two important properties: adaptability and scalability. One of the key hallmarks of CL techniques is the ability to update the models by using only recent data (i.e., without accessing old data). This is often the only practical solution when learning on the edge from high-dimensional streaming or ephemeral data, which would be impossible to keep in memory and process from scratch every time a new piece of information becomes available. Unfortunately, when (deep or shallow) neural networks are trained only on new data, they experience a rapid overriding of their weights with a phenomenon known in the literature as catastrophic forgetting.
To this end, the goal of the CVPR 2020 Workshop on Continual Learning (CLVISION) is to explore methods that generalize to a continuous stream of tasks, incrementally consolidating their knowledge without interfering with previously learned information. Thus, we encourage submissions that address the problems of learning from a few examples, catastrophic forgetting and online learning, large-scale realistic benchmarks, or bio-inspired systems for continual learning, such as memory and plasticity. In this one-day workshop, we will have regular paper presentations, invited speakers, and technical benchmark challenges to present the current state of the art, as well as the limitations and future directions for computer vision in continual learning, arguably one of the most crucial milestones of computer vision and AI in general.
We solicit paper submissions on novel methods and application scenarios of Continual Learning.
TOPICS OF INTEREST (include but are not limited to):
All accepted papers will be presented as posters. Two papers will be selected for oral presentation and one paper will be awarded as the best paper.
CLVision CHALLENGE:
CLVision workshop also provides a comprehensive 2-phase challenge track to thoroughly assess novel continual learning solutions in the computer vision context based on 3 different continual learning (CL) protocols. With this challenge we aim to:
More details on the CLVision Workshop Challenge can be found here: https://sites.google.com/view/clvision2020/challenge.
SUBMISSION GUIDELINES:
IMPORTANT DATES:
Workshop paper submission deadline: March 20th 2020 (11:59 pm Pacific Time)
INVITED SPEAKERS:
ORGANIZERS:
WORKSHOP WEBSITE
PAPER SUBMISSION:
—————————
Thanks and Regards
Nikhil Churamani
PhD Student
University of Cambridge
Department of Computer Science and Technology
William Gates Building
15 JJ Thomson Avenue
Cambridge CB3 0FD
Phone: +44 1223 767024
Email: Nikhil DOT Churamani AT cl.cam.ac.uk
March 11th, 2020
Daniela Lopez de Luise To compete in the challenge and for the full challenge details, please see our competition website (https://competitions.codalab.org/competitions/20597)
Important Dates
=============
Overview
========
To aid in developing computer vision systems that can be easily applied to a robotics domain, our challenge encourages development of probabilistic object detection systems that provide meaningful estimates of both spatial and semantic uncertainty. This enable object detection to be utilised like any other sensor within already trusted Bayesian fusion frameworks
In contrast to traditional object detection challenges (such as COCO), our challenge evaluates detections using the new probability-based detection quality (PDQ) measure which rewards accurate uncertainty estimates, and penalises both overconfident and underconfident detections.
Within the challenge, competitors will detect 30 classes of object in over 56,000 images from 18 high-fidelity simulated video sequences spanning 3 unique environments viewed at 3 different simulated robot heights with both day and night lighting conditions.
As well as the ECCV 2020 PrOD challenge, we have a continuous evaluation server available for those who want to develop work in this field of research.
We invite anyone who is interested in object detection and appreciates a good challenge to please participate and compete in the competition so that we may continue to push the state-of-the-art in object detection in directions more suited to robotics applications.
ECCV 2020 PrOD Competition: https://competitions.codalab.org/competitions/20597
Continuous PrOD Challenge: https://competitions.codalab.org/competitions/20595
Contact Details
============
E-mail: contact@roboticvisionchallenge.org
Twitter: @RobVisChallenge
Website: roboticvisionchallenge.org
March 11th, 2020
Daniela Lopez de Luise Co-located with the ISCA 2020 Conference
(https://iscaconf.org/isca2020/)
May 31, 2020
Valencia, Spain
==================================================================
————————————————————————-
CALL FOR CONTRIBUTIONS
————————————————————————-
In the last 5 years, the remarkable performance achieved in a variety of
application areas (natural language processing, computer vision, games,
etc.) has led to the emergence of heterogeneous architectures to
accelerate machine learning workloads. In parallel, production
deployment, model complexity and diversity pushed for higher
productivity systems, more powerful programming abstractions, software
and system architectures, dedicated runtime systems and numerical
libraries, deployment and analysis tools. Deep learning models are
generally memory and computationally intensive, for both training and
inference. Accelerating these operations has obvious advantages, first
by reducing the energy consumption (e.g. in data centers), and secondly,
making these models usable on smaller devices at the edge of the
Internet. In addition, while convolutional neural networks have
motivated much of this effort, numerous applications and models involve
a wider variety of operations, network architectures, and data
processing. These applications and models permanently challenge computer
architecture, the system stack, and programming abstractions. The high
level of interest in these areas calls for a dedicated forum to discuss
emerging acceleration techniques and computation paradigms for machine
learning algorithms, as well as the applications of machine learning to
the construction of such systems.
————————————————————————-
Links to the Workshop pages
————————————————————————-
Organizers: http://workshops.inf.ed.ac.uk/accml/
ISCA: https://www.iscaconf.org/isca2020/program/workshops.html
————————————————————————-
Invited Speakers
————————————————————————-
– David Kaeli (Northeastern University)
– Antonio González (Universitat Politècnica de Catalunya)
Two additional speakers will be announced before the paper submission
deadline.
————————————————————————-
Topics
————————————————————————-
Topics of interest include (but are not limited to):
– Novel ML systems: heterogeneous multi/many-core systems, GPUs, FPGAs;
– Novel ML hardware accelerators and associated software;
– Emerging semiconductor technologies with applications to ML hardware
acceleration;
– ML for the construction and tuning of systems;
– Cloud and edge ML computing: hardware and software to accelerate
training and inference;
– Computing systems research addressing the privacy and security of
ML-dominated systems.
————————————————————————-
Submission
————————————————————————-
Papers will be reviewed by the workshop's technical program committee
according to criteria regarding a submission's quality, relevance to the
workshop's topics, and, foremost, its potential to spark discussions
about directions, insights, and solutions in the context of accelerating
machine learning. Research papers, case studies, and position papers are
all welcome.
In particular, we encourage authors to submit works-In-Progress papers:
To facilitate sharing of thought-provoking ideas and high-potential
though preliminary research, authors are welcome to make submissions
describing early-stage, in-progress, and/or exploratory work in order to
elicit feedback, discover collaboration opportunities, and generally
spark discussion.
The workshop does not have formal proceedings.
————————————————————————-
Important Dates
————————————————————————-
Submission deadline: May 1, 2020
Notification of decision: May 15, 2020
————————————————————————-
Organizers
————————————————————————-
José Cano (University of Glasgow)
José L. Abellán (Catholic University of Murcia)
Albert Cohen (Google)
Alex Ramirez (Google)
March 11th, 2020
Daniela Lopez de Luise In recent years, we have witnessed extensive breakthroughs in the field of autonomous robotics. One key element of a successful robotic system is the exploitation of the visual and auditory information around the system in order to make decisions. Therefore, machine vision and audition is a major task in most robotic systems. Humans, on the other hand, are very adept at handling and processing visual and auditory stimuli to perform series of tasks such as object detection and identification. The key element in these tasks is the human brain—a complicated organ featuring some billions of neurons and some trillions of synapses (connections) between them. In recent years, due to the rise of parallel-processing hardware (i.e., graphical processing units (GPUs)), we have seen the emergence of deep neural network architectures that attempt to emulate the vastness and complexity of the human brain in order to match its performance. This is particularly evident in machine vision and audition applications, where the emergence of deep learning techniques has boosted the performance of traditional shallow neural network architectures.
The aim of this Special Issue is to present and highlight the newest trends in deep learning for machine vision and audition applications. This may include but is not limited to:
Assoc. Prof. Nikolaos Mitianoudis
Assoc. Prof. Georgios Tzimiropoulos
Guest Editors
Manuscript Submission Information https://www.mdpi.com/journal/electronics/special_issues/deep_learning_machine_vision
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access monthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1400 CHF (Swiss Francs). There are APC waivers and reductions available for . Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
Special Issue Editors
Assoc. Prof. Nikolaos Mitianoudis
Department of Electrical and Computer Engineering, Democritus University of Thrace, 67100 Xanthi, Greece
Assoc. Prof. Georgios Tzimiropoulos
School of Electronic Engineering and Computer Science, Queen Mary University of London, Mile End Road, London E1 4NS, United Kingdom