Instructors: Prof. Dr. Nassir Navab, Dr. Seong Tae Kim, Ashkan Khakzar, Azade Farshad, Dr. Shahrooz Faghih Roohi


  • 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!


  • 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.


  • 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.


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, 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.


DateSession: TopicSlidesStudents
30.01.2020 (16:30-17)Preliminary MeetingSlides
OnlinePaper Assignment

23.04.2020No Class!

30.04.2020No Class!

07.05.2020No Class!

14.05.2020No Class!

28.05.2020Presentation Session 1: Supervised/Weakly-supervised learning
Valeriano Quiroz
04.06.2020Presentation Session 2: Unsupervised/Selfsupervised learning
18.06.2020Presentation Session 3: Data-Efficient DL
25.06.2020Presentation Session 4: Efficient DL
02.07.2020Presentation Session 5: Interpretable DL
09.07.2020Presentation Session 6: Other advanced topics
 Axelrad Tinoco

List of Topics and Material

The list of papers:




TutorStudent (Last name)Link
Supervised (also semi/weakly) and Unsupervised (Self-supervised) Learning1MixMatch: A Holistic Approach to Semi-Supervised LearningNeurIPS 2019TariqIsmaliPDF

2ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring.ICLR 2020SeongTae-PDF

3Unsupervised X-ray image segmentation with task driven generative adversarial networksMedIA 2020ShahroozBornholdtPDF

4f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networksMedIA 2019ShahroozLauenburgPDF

5Temporal cycle-consistency learningCVPR 2019TobiasKondamadugulaPDF

6Neural Bayes: A Generic Parameterization Method for Unsupervised Representation LearningarXiv 2020Azade-PDF

7Automatic 3D Bi-Ventricular Segmentation of Cardiac Images by a Shape-Refined Multi- Task Deep Learning ApproachTMI 2019ShahroozValeriano QuirozPDF

8A robust deep neural network for denoising task-based fMRI data: An application to working memory and episodic memoryMedIA 2020ShahroozCalikPDF
Efficient DL (Lightweight/Faster CNNs / Pruning)9

Search for Better Students to Learn Distilled Knowledge

arXiv 2020



10MetaPruning: Meta Learning for Automatic Neural Network Channel PruningICCV 2019Azade-PDF
Interpretable DL11Explaining Neural Networks Semantically and QuantitativelyICCV 2019Matthias KeicherBordukovaPDF

12Uncertainty and interpretability in convolutional neural networks for semantic segmentation of colorectal polypsMedIA 2020TobiasDanneckerPDF

13Restricting the flow: Information bottlenecks for attributionICLR 2020AshkanElfleinPDF

14Understanding deep networks via extremal perturbations and smooth masksICCV 2019AshkanVagnePDF
Data Efficient DL (Augmentation, learning under noisy label)30FastAutoAugmentNeurIPS 2019SeongTaeStudenyakPDF

15Data Augmentation Using Learned Transformations for One-Shot Medical Image SegmentationCVPR 2019TariqMusatianPDF

16Curriculum Loss: Robust Learning and Generalization against Label CorruptionICLR 2020MagdaDieckmannPDF
Domain Adaptation17Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked TransformationIEEE TMI 2020Farid-PDF

18Action Segmentation with Joint Self-Supervised Temporal Domain AdaptationCVPR 2020Tobias-PDF
Meta-Learning / Few shot learning19Automatic detection of rare pathologies in fundus photographs using few-shot learningMedIA 2020ShahroozChattiPDF

20Meta-Learning Representations for Continual LearningNeurIPS 2019Azade-PDF

Other advanced topics (Uncertainty, GCNs, Disentangled Representation, Noisy Annotations, Multi-label classification, GenerativeModel)22Novelty Detection via BlurringICLR 2020SeongTae-PDF

23AugMix: A Simple Data Processing Method to Improve Robustness and UncertaintyICLR 2020SeongTaeYirikPDF

24Hi-Net: Hybrid-fusion Network for Multi-modal MR Image SynthesisIEEE TMI 2020Farid

25Image-to-Images Translation for Multi-Task Organ Segmentation and Bone Suppression in Chest X-Ray RadiographyIEEE TMI 2020FaridHerrmann


26An improved deep network for tissue microstructure estimation with uncertainty quantificationMedIA 2020Shahrooz

27Combinatorial Inference against Label NoiseNeurIPS 2019SeongTae

28Multi-task learning for the segmentation of organs at risk with label dependenceMedIA 2020MagdaAxelrad TinocoPDF

29Disentangled representation learning in cardiac image analysisMedIA 2019Shahrooz

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:

Some publishers:

Libraries (online and offline):

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.

  • No labels