[visionlist] NIPS 2018 Workshop: Compact Deep Neural Network Representation with Industrial Applications

Lixin Fan lixin.fan01 at gmail.com
Mon Sep 10 02:56:16 -05 2018


Compact Deep Neural Network Representation with Industrial Applications

NIPS 2018 Workshop

Friday, December 7, 2018

Palais des Congrès de Montréal, Montréal, Canada


This workshop aims to bring together researchers, educators, practitioners
who are interested in techniques as well as applications of making compact
and efficient neural network representations. One main theme of the
workshop discussion is to build up consensus in this rapidly developed
field, and in particular, to establish close connection between researchers
in machine learning community and engineers in industry.  We believe the
workshop is beneficial to both academic researchers as well as industrial


. the workshop NIPS webpage:

. the workshop html webpage is online at

. the workshop OpenReview submission site is online at


. Notice: the workshop submission deadline is changed to 20 Oct 2018 (see
below) !

. We will help authors of accepted submissions to get access to a reserve
pool of NIPS tickets.  So please register to the workshop early.

Call for submissions

We invite you to submit original work in, but not limited to, following

Neural network compression techniques:

Binarization, quantization, pruning, thresholding and coding of neural

Efficient computation and acceleration of deep convolutional neural networks

deep neural network computation in low power consumption applications
(e.g., mobile or IoT devices)

Differentiable sparsification and quantization of deep neural networks

Benchmarking of deep neural network compression techniques

Neural network representation and exchange

Exchange formats for (trained) neural networks

Efficient deployment strategies for neural networks

Industrial standardization of deep neural network representations

Performance evaluation methods of compressed networks in application
context (e.g., multimedia encoding and processing)

Video & media compression methods using DNNs such as those developed in
MPEG group:

To improve video coding standard development by using deep neural

To increase practical applicability of network compression methods

An extended abstract (3 pages long using NIPS style, see
https://nips.cc/Conferences/2018/PaperInformation/StyleFiles) in PDF format
should be submitted for evaluation of the originality and quality of the
work.  The evaluation is double-blind and the abstract must be anonymous.
References may extend beyond the 3 page limit, and parallel submissions to
a journal or conferences (e.g. AAAI or ICLR) are permitted.

Submissions will be accepted as contributed talks (oral) or poster
presentations. Extended abstract should be submitted by 20 Oct 2018 through
OpenReview.  Submission details will be updated at the workshop website
http:address_here.  All accepted abstracts will be posted on the workshop
website and archived.  The full papers of all accepted abstracts will be
recommended for considering publication at an international journal.

Important dates

Extended abstract submission deadline:  20 Oct 2018,  (3̶1̶ ̶O̶c̶t̶

Acceptance notification: 29 Oct. 2018,  (1̶6̶ ̶N̶o̶v̶e̶m̶b̶e̶r̶ ̶2̶0̶1̶8̶)

Camera ready submission: 12 November 2018, (3̶0̶ ̶N̶o̶v̶e̶m̶b̶e̶r̶

Workshop: 7 December 2018


Submit your extended abstract through OpenReivew system (click here)

Workshop schedule (tentative):

09:00 AM            Opening and Introduction (Talk)

09:05 AM            TBD 1 (Oral presentation)

09:30 AM            Bandwidth efficient deep learning by model compression
(Invited talk) Song Han, MIT and Deephi

09:55 AM            Neural network compression in the wild: why aiming for
high compression factors is not enough (Invited talk)  Tim Genewein, Bosch
Center for AI and DeepMind

10:20 AM            TBD 2 (Oral presentation)

10:45 AM            Coffee break (morning) (break)

11:00 AM            Network compression via differentiable pruning and
quantization (Invited talk) Christos Louizos

11:25 AM            Deep neural networks for multimedia processing, coding
and standardization (Invited talk)  Shan Liu, Tencent Media Lab

11:50 AM            TBD 3 (Oral presentation)

12:15 PM             Lunch break (on your own) (break)

02:00 PM             Efficient Computation of Deep Convolutional Neural
Networks: A Quantization Perspective (Invited talk) Jian Cheng, Institute
of Automation, China

02:25 PM             Deep neural network compression and acceleration
(Invited talk) Anbang Yao, Intel labs China

02:50 PM             TBD 4 (Oral presentation)

03:15 PM             Coffee break (afternoon) (break)

03:30 PM             Poster presentations TBD (Poster session)

04:30 PM             Panel disucssion

05:30 PM             Invited talk (TBD) (Invited talk)

05:55 PM             Closing (Talk)

NIPS Complimentary workshop registration:

We will help authors of accepted submissions to get access to a reserve
pool of NIPS tickets.  So please register to the workshop early.


Lixin Fan, Nokia Technologies <lixin.fan at nokia.com>

Zhouchen Lin, Peking University <zlin at pku.edu.cn>

Max Welling, Qualcomm & University of Amsterdam,  <welling.max at gmail.com>

Yurong Chen, Intel Labs China,  <yurong.chen at intel.com>

Werner Bailer, Joanneum Research, <werner.bailer at joanneum.at>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20180910/0b28a7a1/attachment.html>

More information about the visionlist mailing list