|See pictures of previous editions: Set1 - Set2
Reading Group - Rules of Engagement
During a typical PhD, students will read probably more than 100 papers. Reading research papers is a skill that can be acquired and that is very different from reading a novel. The reading group sessions at MISS are to introduce students to that skill. In small groups of around 10-15 students per faculty member, students will discuss papers selected by the school faculty. In preparation for this, students are expected to study (not just read) the provided papers in advance, by tracing the ideas in those papers as far back as possible.
At MISS, we will be holding two different types of reading groups:
Introductory Reading Group: On Monday at 16:45 after the lectures, we will run an introductory reading group for all school participants, introducing the concept of how to critically read a paper, with an example paper for all to read and work through ahead of school. This will be held on Monday after the lectures, and will be led by Julia Schnabel. The introductory reading group is a useful example of how Deep Learning can solve a Medical Imaging task.
The introductory paper is the following
Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Konstantinos Kamnitsas, Christian Ledig, Virginia F.J. Newcombe, Joanna P. Simpson, Andrew D. Kane, David K. Menon, Daniel Rueckert, Ben Glocker. Medical Image Analysis 36 (2017) 61-78, doi.org/10.1016/j.media.2016.10.004
Read it before coming to the school!
Individual Reading Groups: parallel reading groups will be held, led by individual MISS lecturers on a paper of their suggestions. These will take place in small groups of students informally over lunch (at everyone’s own expense), and will give you a great opportunity to personally meet and work closely with one of the MISS lecturers, and vice versa. We expect this to be a hugely enjoyable experience, and hope that you will share “your” lecturer’s enthusiasm on the paper they suggested – especially if these are their own ones! Every student will receive information about his/her group by email. Unfortunately there is no assignment that will satisfy all participants, so in the interest of fairness the groups have been divided randomly. This means that students cannot change their assigned group.
The different groups are reported below in the section “GROUPS”. Please carefully read and work through your allocated paper before arriving at the school.
is no single right way of how to read a scientific paper, but you may
find the following guidelines helpful:
starting to read a paper, don’t read it front to back straight away.
Instead, you can use the following 3-stage process:
Screening: Read the title and abstract, and then flick through the
pages to look at any illustrations, pictures and plots, and the final
summary and conclusions. Now, set the paper aside and ask yourself
a number of questions: what is the paper about? What problem does
it purport to help solve? Is the problem important or of interest
to me? If I were to tackle this problem, how would I do it? This quick
skim will take you just a few minutes and is often the decisive factor
on whether you actually want to delve deeper into this paper or instead
find a more interesting one to read (of course, in this school, you
will still need to read the paper!). It’s similar to reading
the “blurbs” of a paperback novel, or the first page of
a newspaper. However, if you ask yourself the above questions you
are already actively engaging with the paper in a way that you do
not when you are reading a novel!
the punchline: On your second pass, you should read the paper front
to back, but leave out any equations or complicated descriptions,
so that you don’t slow down your progress through the paper.
Your aim on this pass is to try to understand the key ideas of the
paper, whilst avoiding to get bogged down by any technical/mathematical
details. Again, set the paper aside and ask yourself some more questions:
Does the paper propose a method – in which case, does it work?
Does it work on real data or just on simulated (numerical) data? What
are the limitations of the approach? What are the novelties/strengths?
Is the approach something that you might use in your work? Note that
you can generally answer all of these questions without understanding
a single equation! Again, you are actively engaging with the paper,
this time to establish the key ideas presented, which may whet your
appetite to go one step further.
Understanding the paper: This requires a third pass (and a fourth,
fifth… pass), when you read the paper much more carefully, trying
to work through all the nitty-gritty detail. This will involve looking
at references in this work, and can easily become a recursive problem
as you will start reading more and more papers in order to make sense
of the first one. However, do not get disheartened as you often only
need to find the key idea (steps 1 and 2) of those papers in order
to understand your paper. You can always return later to the more
interesting ones and read them more thoroughly. This is a great way
of building up your own library of papers. Note that Google Scholar,
ResearchGate and other tools allow you to also go “back to the
future”, as for a given paper, you can find out which later
(more recent) papers have cited and built up on it. This is often
used to establish the “impact” of a paper. However, don’t
be completely fooled by any odd “highly-cited papers”
– they could receive a lot of citations for being a particularly
bad example of a technique or application!
any of the steps above, try to switch between roles of reader/reviewer
and author. This will ultimately help you in writing better papers. To
Be critical: Do not believe everything that’s written in a paper,
but use your own judgment and (ever growing) experience. Question
the problem statement, motivation, timeliness and importance of the
work. Consider any assumptions made, and whether much simpler methods
could have been used rather than elaborate new methods. Check whether
a new method was compared to the state-of-the-art and whether it was
properly validated. The number of datasets, any quantitative values
in form of tables, graphs or plots are good indicators. Check for
any “magic parameters” and whether these have been tested.
Make a list of what improvements to this work could be done, like
a scientific reviewer for a journal or conference would do.
Be constructive: Try to find the key idea / main innovation of the
paper. Reviewers are often very critical (see above), but normally
would try to start their review by stating the contributions of the
work, and what they really like about it. When collecting the good
points of a paper, you can also think about how ideas generated by
a paper could be translated to other methods or applications (the
authors usually indicate this in their outlook section). The introductory
reading group paper (see above) is perhaps a useful example of how
an idea generated in Computer Vision could find its way into Medical
courteous: It is very easy to “dress down” a paper –
but putting yourself into the authors’ position may help you
see that some limitations cannot be overcome very easily; comparison
to other methods may not always be possible due to lack of openly
available source code/data or a difference in underlying assumptions.
Sometimes, even if a paper does not contain an entirely new method,
validation, or useful application, there may still be the grain of
an idea for future papers!
Be thorough: highlight passages, take notes, work through mathematical
derivations, and even write a brief summary of a paper that you read.
When presenting a paper in your own lab, you could make up a few slides
with bullet points of the key bits of the paper, using figures from
the paper for better visualisation. If any source code is available,
download it and try it out on provided or your own data – or
even re-implement it yourself.
Set your ego to one side: Often, a review says “This paper is
quite good but omits reference to Foobar et. al. [1,…,2624].
The author will immediately know that the reviewer is Foobar, or one
of his/her colleagues, and any reasonable Editor will ignore this
comment. Science does not progress so that my success is inevitably
your failure. Be generous in your assessment of other peoples’
work, even if they do omit mention to your 2624 defining contributions
on the topic which, in your unbiased judgement close off forever that
line of work and establishing you as the world authority.
your own “verdict”: In rare cases this could be completely
thumbs up or down (after your critical, constructive, courteous, thorough
and generous study process of course!), but more often will turn out
to be much more nuanced, summarising the various pro’s and con’s,
and the potential impact of the paper to stimulate new ideas.
are in fact papers (as well as books, websites and blogs) on how to read
papers – be your own judge on how good those papers are! Here is
just a small selection:
there are papers providing helpful guidelines on how to review a paper,
where our personal favourite stipulates the golden rule of reviewing:
“treat other manuscripts as you would want your own to be treated”!
Here another small selection:
Every MISS student will receive an email with indication of their group.
GROUP 1: Tuesday 13:30-15:00
MolGAN: An implicit generative model for small molecular graphs. Nicola De Cao, Thomas Kipf. https://arxiv.org/abs/1805.11973
GROUP 2: Tuesday 13:30-15:00
Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation. Ozan Oktay, Enzo Ferrante, Konstantinos Kamnitsas, Mattias Heinrich, Wenjia Bai, Jose Caballero, Stuart A. Cook, Antonio de Marvao, Timothy Dawes, Declan P. O'Regan, Bernhard Kainz, Ben Glocker, Daniel Rueckert. https://ieeexplore.ieee.org/abstract/document/8051114
GROUP 3: Tuesday 13:30-15:00
Large scale deep learning for computer aided detection of mammographic lesions. Thijs Kooi, Geert Litjens, Bramvan Ginneken, Albert Gubern-Mérida, Clara I.Sánchez, RitseMann. 10.1016/j.media.2016.07.007
GROUP 4: Tuesday 13:30-15:00
Mathematics of Deep Learning. René Vidal, Joan Bruna, Raja Giryes, Stefano Soatto. 2017. https://arxiv.org/abs/1712.04741
GROUP 5: Tuesday 13:30-15:00
Image-to-Image Translation with Conditional Adversarial Networks. Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 5967-5976. 10.1109/CVPR.2017.632
GROUP 6: Tuesday 13:30-15:00
Mask R-CNNK. Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick. 2017 IEEE International Conference on Computer Vision (ICCV). 10.1109/ICCV.2017.322
GROUP 7: Thursday 13:30-15:00
Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs. Maxim Tatarchenko, Alexey Dosovitskiy, Thomas Brox. 2017 IEEE International Conference on Computer Vision (ICCV). https://lmb.informatik.uni-freiburg.de/Publications/2017/TDB17b/
GROUP 8: Thursday 13:30-15:00
Learning to Reason: End-to-End Module Networks for Visual Question Answering. Ronghang Hu, Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Kate Saenko. 2017 IEEE International Conference on Computer Vision (ICCV). 10.1109/ICCV.2017.93
GROUP 9: Thursday 13:30-15:00
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. Chelsea Finn, Pieter Abbeel, Sergey Levine. 2017 International Conference on Machine Learning (ICML). https://arxiv.org/abs/1703.03400
GROUP 10: Tuesday 13:30-15:00
Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation. Adrian V. Dalca, John Guttag, Mert R. Sabuncu. 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). http://openaccess.thecvf.com/content_cvpr_2018/papers/Dalca_Anatomical_Priors_in_CVPR_2018_paper.pdf
GROUP 11: Thursday 13:30-15:00
Dynamic Routing Between Capsules. Sara Sabour, Nicholas Frosst, Geoffrey E Hinton. https://arxiv.org/abs/1710.09829
GROUP 12: Thursday 13:30-15:00
The Building Blocks of Interpretability. Olah, Chris and Satyanarayan, Arvind and Johnson, Ian and Carter, Shan and Schubert, Ludwig and Ye, Katherine and Mordvintsev, Alexander. https://distill.pub/2018/building-blocks/