Instructors: Prof. Dr. Nassir Navab, Dr. Seong Tae Kim, Ashkan Khakzar, Azade Farshad, Dr. Shahrooz Faghih Roohi
Announcements
- Due to the COVID-19, the seminar would be held in the virtual lecture room at least initially, and potentially the whole semester (we will announce the detailed information on the website).
- 31-01-2020: Slides for the preliminary meeting are available
- 22-01-2020: Preliminary meeting: Thursday, 30.01.2020 (16:30-17:00) in CAMP Seminar Room, 03.13.010.
- 20-01-2020: Website is up!
Introduction
- Deep Learning is growing tremendously in Computer Vision and Medical Imaging as well. Highly impacted journals in the medical imaging community, i.e. IEEE Transaction on Medical Imaging, published recently their special edition on Deep Learning [1]. The Seminar will propose a list of recent scientific articles related to the main current research topics in deep learning for Medical Applications together with some interesting papers from other communities.
Registration
- Interested students should attend the introductory meeting to enlist in the course.
- Students can only register through TUM Matching Platform themselves if the maximum number of participants hasn't been reached (please pay attention to the Deadlines).
- The maximum number of participants: 20.
Requirements
In this Master Seminar (formerly Hauptseminar), each student is asked to send three preferences from the list, then he will be assigned one paper. In order to successfully complete the seminar, participants have to fulfill these requirements:
- Presentation: The selected paper is presented to the other participants (20 minutes presentation 10 minutes questions). Use the CAMP templates for PowerPoint camp-tum-jhu-slides.zip, or Latex: CAMP-latex-template.
- Blog Post: A blog post of 1000-1500 words excluding references should be submitted before the deadline.
- Attendance: Participants have to participate actively in all seminar sessions.
The students are required to attend each seminar presentation which will be held during this course. Each presentation is followed by a discussion and everyone is encouraged to actively participate. The blog post must include all references used and must be written completely in your own words. Copy and paste will not be tolerated. Both the blog post and presentation have to be done in English.
You need to upload your presentation and blog post here. More details will be provided before the beginning of the semester.
Submission Deadline: You have to submit both the presentation and the blog post two weeks right after your presentation session.
Schedule
| Date | Session: Topic | Slides | Students |
|---|---|---|---|
| 30.01.2020 (16:30-17) | Preliminary Meeting | Slides | |
| Online | Paper Assignment | ||
| 23.04.2020 | No Class! | ||
| 30.04.2020 | No Class! | ||
| 07.05.2020 | No Class! | ||
| 14.05.2020 | No Class! | ||
| 28.05.2020 | Presentation Session 1: Supervised/Weakly-supervised learning | Isamli Valeriano Quiroz Calik | |
| 04.06.2020 | Presentation Session 2: Unsupervised/Selfsupervised learning | Bornholdt Lauenburg Kondamadugula | |
| 18.06.2020 | Presentation Session 3: Data-Efficient DL | Studenyak Musatian Dieckmann | |
| 25.06.2020 | Presentation Session 4: Efficient DL | Wang Chatti Breitinger | |
| 02.07.2020 | Presentation Session 5: Interpretable DL | Bordukova Dannecker Elflein Vagne | |
| 09.07.2020 | Presentation Session 6: Other advanced topics | Herrmann Axelrad Tinoco |
List of Topics and Material
The list of papers:
| Topic | No | Title | Conference/ Journal | Tutor | Student (Last name) | Link |
|---|---|---|---|---|---|---|
| Supervised (also semi/weakly) and Unsupervised (Self-supervised) Learning | 1 | MixMatch: A Holistic Approach to Semi-Supervised Learning | NeurIPS 2019 | Tariq | Ismali | |
| 2 | ICLR 2020 | SeongTae | - | |||
| 3 | Unsupervised X-ray image segmentation with task driven generative adversarial networks | MedIA 2020 | Shahrooz | Bornholdt | ||
| 4 | f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks | MedIA 2019 | Shahrooz | Lauenburg | ||
| 5 | Temporal cycle-consistency learning | CVPR 2019 | Tobias | Kondamadugula | ||
| 6 | arXiv 2020 | Azade | - | |||
| 7 | Automatic 3D Bi-Ventricular Segmentation of Cardiac Images by a Shape-Refined Multi- Task Deep Learning Approach | TMI 2019 | Shahrooz | Valeriano Quiroz | ||
| 8 | A robust deep neural network for denoising task-based fMRI data: An application to working memory and episodic memory | MedIA 2020 | Shahrooz | Calik | ||
| Efficient DL (Lightweight/Faster CNNs / Pruning) | 9 | Search for Better Students to Learn Distilled Knowledge | arXiv 2020 | Wang | ||
| 10 | ICCV 2019 | Azade | - | |||
| Interpretable DL | 11 | Explaining Neural Networks Semantically and Quantitatively | ICCV 2019 | Matthias Keicher | Bordukova | |
| 12 | Uncertainty and interpretability in convolutional neural networks for semantic segmentation of colorectal polyps | MedIA 2020 | Tobias | Dannecker | ||
| 13 | Restricting the flow: Information bottlenecks for attribution | ICLR 2020 | Ashkan | Elflein | ||
| 14 | Understanding deep networks via extremal perturbations and smooth masks | ICCV 2019 | Ashkan | Vagne | ||
| Data Efficient DL (Augmentation, learning under noisy label) | 30 | FastAutoAugment | NeurIPS 2019 | SeongTae | Studenyak | |
| 15 | Data Augmentation Using Learned Transformations for One-Shot Medical Image Segmentation | CVPR 2019 | Tariq | Musatian | ||
| 16 | Curriculum Loss: Robust Learning and Generalization against Label Corruption | ICLR 2020 | Magda | Dieckmann | ||
| Domain Adaptation | 17 | IEEE TMI 2020 | Farid | - | ||
| 18 | CVPR 2020 | Tobias | - | |||
| Meta-Learning / Few shot learning | 19 | Automatic detection of rare pathologies in fundus photographs using few-shot learning | MedIA 2020 | Shahrooz | Chatti | |
| 20 | NeurIPS 2019 | Azade | - | |||
| 21 | META-LEARNING UPDATE RULES FOR UNSUPERVISED REPRESENTATION LEARNING | ICLR 2019 | Azade | Breitinger | ||
| Other advanced topics (Uncertainty, GCNs, Disentangled Representation, Noisy Annotations, Multi-label classification, GenerativeModel) | 22 | ICLR 2020 | SeongTae | - | ||
| 23 | ||||||
| 24 | IEEE TMI 2020 | Farid | ||||
| 25 | Image-to-Images Translation for Multi-Task Organ Segmentation and Bone Suppression in Chest X-Ray Radiography | IEEE TMI 2020 | Farid | Herrmann | ||
| 26 | MedIA 2020 | Shahrooz | ||||
| 27 | NeurIPS 2019 | SeongTae | ||||
| 28 | Multi-task learning for the segmentation of organs at risk with label dependence | MedIA 2020 | Magda | Axelrad Tinoco | ||
| 29 | MedIA 2019 | Shahrooz |
MICCAI: Medical Image Computing and Computer Assisted Intervention
CVPR: Conference on Computer Vision and Pattern Recognition
ICLR: International Conference on Learning Representations
TMI: IEEE Transaction on Medical Imaging
JBHI: IEEE Journal of Biomedical and Health Informatics
MedIA: Medical Image Analysis (Elsevier)
TPAMI: IEEE Transactions on Pattern Analysis and Machine Intelligence
BMVC: British Machine Vision Conference
MIDL: Medical Imaging with Deep Learning
NeurIPS: Neural Information Processing Systems
Literature and Helpful Links
A lot of scientific publications can be found online.
The following list may help you to find some further information on your particular topic:
- Microsoft Academic Search
- Google Scholar
- CiteSeer
- CiteULike
- Collection of Computer Science Bibliographies
Some publishers:
- ScienceDirect (Elsevier Journals)
- IEEE Journals
- ACM Digital Library
Libraries (online and offline):
- http://rzblx1.uni-regensburg.de/ezeit/ (Elektronische Zeitschriften Bibliothek)
- Verbundkatalog des Bibliotheksverbundes Bayern (BVB)
- Computer ORG
- http://www.ub.tum.de/ (TUM Library)
- To get access onto the electronic library, see http://www.ub.tum.de/medien/ejournals/readme.html
- "proxy.biblio.tu-muenchen.de" mit Port 8080 (nur fuer http). Damit klappen zumindest portal.acm.org und computer.org meistens
- Various proceedings of conferences in our AR-Lab, 03.13.036 (These proceedings are not for lending!)
Some further hints for working with references:
- JabRef is a Java program for comfortable working with Bibtex literature databases. Handy feature: if you know the PubMed ID for an article, JabRef can import data from there (via "Web Search/Medline").
- Mendeley is a cross-platform program for organising your references.
If you find useful resources that are not already listed here, please tell us, so we can add them for others. Thanks.