[visionlist] PhD offer "Transfer Learning for Material classification based on visual appearance correspondences" at University of Saint-Etienne, France

Tremeau alain.tremeau at univ-st-etienne.fr
Mon Mar 26 07:23:29 -05 2018

Ph.D position in/Material classification based on visual appearance/

The Image Science and Computer Vision team of Hubert Curien laboratory 
(https://laboratoirehubertcurien.univ-st-etienne.fr/en/index.html) is 
looking for candidates for a Ph.D position on /Transfer Learning for 
Material classification based on visual appearance correspondences/.

Image classification has received a lot of interest in the last decade 
and huge improvements have been observed in terms of classification 
accuracy for the classical datasets such as PASCAL VOC or ImageNet. 
Nevertheless, it appears that material classification is still an open 
problem because of the high variability of their appearance in images 
and because of the lack of learning data. In order to cope with these 
problems, recent papers resort to convolutional networks 
(https://arxiv.org/ftp/arxiv/papers/1710/1710.06854.pdf) in order to 
learn the variability as well as transfer learning approaches in order 
to be able to learn on different datasets and so increasing the amount 
of learning data (https://arxiv.org/pdf/1609.06188.pdf).

The aim of this PhD project is to study the visual appearance of 
materials from a computer vision perspective by combining computer 
vision techniques with machine learning and data mining techniques. More 
and more the design of new materials having specific visual appearance 
properties passes through the use of computer based approaches (see ref 
3, 4 and 5).

The objective will be:

1.To study different strategies to fuse/combine different datasets, to 
enrich existing datasets using data augmentation methods (e.g. light 
variations, scale, shadows, …), to transfer knowledge learnt from one 
dataset to another one (e.g. see https://arxiv.org/pdf/1609.06188.pdf), 
to mind/infer knowledge from data, etc.

2.To create a new dataset of images of materials which could be 
complementary to the existing synthetized and real-world ones: Flickr 
Material Database (Sharan et al., 2010), the ImageNet7 dataset (Hu et 
al., 2011), the MINC-2500 (Bell et al., 2015), the University of Bonn 
synthetic dataset (Weinmann et al., 2014), …

3.To classify images of materials according their visual appearance in 
order to infer/learn new knowledge on material properties (for example 
using auto-encoders, see https://arxiv.org/pdf/1711.03678.pdf). Several 
machine learning and data mining methods (e.g. CNN, deep learning, will 
be investigated.

4.To learn how to characterize the visual appearance of some materials 
from a limited set of features and of image acquisitions. The 
auto-encoder could be a nice tool to access semantic features and 
observe their impact on the reconstructed material images. This could 
also help for material design.

The thesis will be co-supervised by Alain Trémeau (Full Professor, 
https://perso.univ-st-etienne.fr/tremeaua/) and Damien Muselet 
(Assistant Professor,https://perso.univ-st-etienne.fr/muda8804/).

*The deadline for applications is 06/05/2018.*


1.Sébastien Lagarde, “Open Problems in Real-Time 
Rendering-Physically-Based Materials: Where Are We?” in ACM SIGGRAPH 

2.(2018) G. Kalliatakis, A. Sticlaru, G. Stamatiadis, S. Ehsan, A. 
Leonardis, J. Gall and K. D. McDonald-Maier, Material Classification in 
the Wild: Do Synthesized Training Data Generalise Better than Real-world 
Training Data?Proceedings of VISAPP’2018.__

3.(2018) Reviewing the Novel Machine Learning Tools for Materials 
Design. https://link.springer.com/chapter/10.1007/978-3-319-67459-9_7;

4.(2017) Data mining-aided materials discovery and 

5.(2017) ^Materials discovery and design using machine learning, 

6.(2016) An intuitive control space for material appearance*, 

    Requested skills

The desired profile is Master (MSc or equivalent) or Engineer degree in 
Machine Learning and Data Mining / Image Processing and Computer Vision 
/ Computer Science and Applied Mathematics, with excellent academic 
record and research experience, in-depth knowledge of machine learning 
(Computational Neural Networks, Deep Learning), data mining (Transfer 
Knowledge), optimization methods, with a specialization in one of the 
following areas: machine learning, data mining or computer vision.

We are looking for a curious student with excellent programming skills 
(e.g., in Matlab, Python, or C/C++).


Interested candidates should send a resume, a cover letter, and 
transcripts of BSc and MSc (M1 and M2 years). Recommendation letters 
will be appreciated.

All applications must be sent electronically to Alain Trémeau 
(alain.tremeau at univ-st-etienne.fr 
<mailto:alain.tremeau at univ-st-etienne.fr>) and Damien Muselet 
(damien.muselet at univ-st-etienne.fr 
<mailto:damien.muselet at univ-st-etienne.fr>)


3-years contract on the basis of a monthly gross income of 1 760 euros 
approximatively. Part-time teaching can be considered. Start in autumn 2018.


Alain Tremeau
Academic Coordinator of Masters COSI/CIMET and 3DMT, 
http://www.master-colorscience.eu/, http://master-3dmt.eu/
Visit my homepage: http://perso.univ-st-etienne.fr/tremeaua/
alain.tremeau at univ-st-etienne.fr <mailto:alain.tremeau at univ-st-etienne.fr>
Tél. : 04 77 91 57 52

Laboratoire Hubert Curien
Image Science & Computer Vision Group
Campus Manufacture
23 RUE Dr Paul Michelon
04 77 91 57 80



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20180326/b51a29ab/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: afaedchmjjaagcjh.png
Type: image/png
Size: 1943 bytes
Desc: not available
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20180326/b51a29ab/attachment-0008.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: idlpfdhenangillh.png
Type: image/png
Size: 1710 bytes
Desc: not available
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20180326/b51a29ab/attachment-0009.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: mhcgahafjkfbdhch.png
Type: image/png
Size: 226 bytes
Desc: not available
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20180326/b51a29ab/attachment-0010.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: honaphhfdembahhf.png
Type: image/png
Size: 257 bytes
Desc: not available
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20180326/b51a29ab/attachment-0011.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: dcmcmdgfpdpfnfip.png
Type: image/png
Size: 333 bytes
Desc: not available
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20180326/b51a29ab/attachment-0012.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: ikdpnggjjibehilp.png
Type: image/png
Size: 235 bytes
Desc: not available
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20180326/b51a29ab/attachment-0013.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: cjcchmcdmceflici.png
Type: image/png
Size: 304 bytes
Desc: not available
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20180326/b51a29ab/attachment-0014.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: gjblmipkemiaflbb.png
Type: image/png
Size: 1218 bytes
Desc: not available
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20180326/b51a29ab/attachment-0015.png>

More information about the visionlist mailing list