• Angelegt von Unbekannter Benutzer (ga59mat), zuletzt geändert am 20. April 2021

Instructors: Prof. Dr. Nassir Navab, Dr. Shahrooz Faghih Roohi,  Ashkan Khakzar, Azade Farshad, Roger Soberanis


Time: Thursdays, 12:00 to 14:00

Registration

Announcements

  • The presentation guidelines are available here: Guide_DLMAss21.pdf
  • The preliminary meeting slides can be found here: DLMASs21.pdf
  • The preliminary meeting is scheduled for Feb 8, 15:30 (Zoom link is visible on TUMonline in the course description).
  • Due to the current pandemic, the seminar happens virtually via Zoom (the meeting link will be shared with participants via email).

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 (CVPR, NeurIPS, ICCV, ICLR, ICML, ...).

Course Structure

In this Master Seminar (Hauptseminar), students select one scientific article from the list provided by course organizers. The students read the paper, and must accomplish the following:

  • Presentation: The selected paper is presented to the other participants (20 minutes presentation 10 minutes questions). You can use the CAMP templates for PowerPoint camp-tum-jhu-slides.zip, or Latex: CAMP-latex-template.
  • Blog Post: A blog post of 1000-1200 words excluding references should be submitted before the deadline. The blog post must include all references used and must be written completely in your own words. Copy and paste will not be tolerated
  • Attendance: Participants have to participate actively in all seminar sessions. Each presentation is followed by a discussion and everyone is encouraged to actively participate.

Submission Deadline: You have to submit the blog post one week before your presentation session! You should also submit the presentation one day right after your presentation session.

You may look at the blog posts and presentations from the previous semester (using the tree in the upper left corner).

Schedule

DateSession: TopicSlidesStudents
08.02.2021 (15:30-16)Preliminary MeetingSlides
13.04.2021Announcing the list of papers


19.04.2021Paper Assignment

20.05.2021Data-Efficient DL, Representation Learning 1

Ana-Maria Lacatusu

Oleksii Khakhlyuk

27.05.2021Data-Efficient DL, Representation Learning 2

Rob van Kemenade

Melissa Lutgardo

Yiran Huang

03.06.2021No class (regional holiday)

10.06.2021Unsupervised/Semi-supervised/Self-supervised learning 1

Zhisheng Zheng

Huaiwei Zhang

Florian Hautmann

17.06.2021Unsupervised/Semi-supervised/Self-supervised learning 2

Tomas Chobola

Margaryta Olenchuk

Batuhan Yumurtaci

24.06.2021Transformers

Güven Erkaya

Mei-Ju Su

01.07.2021Medical Image segmentation / Registration/ Report generation

Lizi Mamisashvili

Cansu Yildirim

Tim Neumann

08.07.2021Graph

Zhuoling Li

Carl Alexander Noack

Ayhan Can Erdur

List of Topics and Material

Papers in this course are selected from the following venues/publications:


CVPR: Conference on Computer Vision and Pattern Recognition
ICLR: International Conference on Learning Representations
NeurIPS: Neural Information Processing Systems

TPAMI: IEEE Transactions on Pattern Analysis and Machine Intelligence

TMI: IEEE Transaction on Medical Imaging
JBHI: IEEE Journal of Biomedical and Health Informatics
MedIA: Medical Image Analysis (Elsevier)

MICCAI: Medical Image Computing and Computer-Assisted Intervention
BMVC: British Machine Vision Conference
MIDL: Medical Imaging with Deep Learning


List of papers

TopicNoTitleJournal/ ConferenceTutorStudentLink
Medical Image segmentation / Registration/ Report generation1Automatic Medical Image Report Generation with Multi-view and Multi-modal Attention MechanismICA3PP 2020MatthiasLizi Mamisashvilihttps://link.springer.com/chapter/10.1007/978-3-030-60248-2_48

3CS2-Net: Deep learning segmentation of curvilinear structures in medical imagingMedIA 2020ShahroozCansu Yildirimhttps://www.sciencedirect.com/science/article/abs/pii/S1361841520302383

4Learning multiview 3D point cloud registration CVPR 2020MariaTim Neumannhttps://openaccess.thecvf.com/content_CVPR_2020/html/Gojcic_Learning_Multiview_3D_Point_Cloud_Registration_CVPR_2020_paper.html







Unsupervised/Semi-supervised/Self-supervised learning5Rubik's Cube+: A Self-supervised Feature Learning Framework for 3D Medical Image AnalysisMedIA 2020Shahrooz-----------https://www.sciencedirect.com/science/article/abs/pii/S1361841520301109

6SELF-SUPERVISED LEARNING FROM A MULTI-VIEW PERSPECTIVEICLR 2021AzadeHuaiwei Zhanghttps://openreview.net/pdf?id=-bdp_8Itjwp

7Self-supervised Pretraining of Visual Features in the WildCVPR 2021TariqTomas Chobolahttps://arxiv.org/pdf/2103.01988.pdf

8Big Self-Supervised Models Advance Medical Image ClassificationsCVPR 2021TariqFlorian Hautmannhttps://arxiv.org/pdf/2101.05224.pdf

10Semi-Supervised Capsule cGAN for Speckle Noise Reduction in Retinal OCT ImagesTMI 2021ShahroozMargaryta Olenchukhttps://ieeexplore.ieee.org/abstract/document/9312620

11State-Aware Tracker for Real-Time Video Object SegmentationCVPR2020Baochang ZhangBatuhan Yumurtacihttps://arxiv.org/pdf/2003.00482.pdf

2Unifying Neural Learning and Symbolic Reasoning for Spinal Medical Report GenerationMedical Image Analysis, 2021MatthiasZhisheng Zheng

https://www.sciencedirect.com/science/article/abs/pii/S136184152030236X?dgcid=rss_sd_all









9Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation LearningCVPR 2021HeikoOleksii Khakhlyukhttps://arxiv.org/abs/2011.10043
Data-Efficient DL, Representation Learning12Continual Adaptation of Visual Representations via Domain Randomization and Meta-learningCVPR 2021AzadeMelissa Lutgardohttps://arxiv.org/pdf/2012.04324.pdf

13Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain AdaptationCVPR 2021Azade-----------https://arxiv.org/pdf/2103.16765.pdf

14Handling Missing Data with Graph Representation LearningNeurIPS 2020RogerYiran Huanghttps://arxiv.org/abs/2010.16418

15Procedure Planning in Instructional VideosECCV 2020TobiasAna-Maria Lacatusuhttps://arxiv.org/pdf/1907.01172.pdf

20Saliency is a Possible Red Herring When Diagnosing Poor GeneralizationICLR 2021AshkanRob van Kemenadehttps://arxiv.org/abs/1910.00199







Reliable AI (Interpretability, Uncertainty, robustness)16On Modelling Label Uncertainty in Deep Neural Networks: Automatic Estimation of Intra- Observer Variability in 2D Echocardiography Quality AssessmentTMI 2020Roger-----------https://ieeexplore.ieee.org/document/8932548

17Neural Response Interpretation through the Lens of Critical PathwaysCVPR 2021Ashkan-----------https://arxiv.org/abs/2103.16886

18Rethinking the Role of Gradient-Based Attribution Methods for Model InterpretabilityICLR 2021Ashkan-----------https://arxiv.org/abs/2006.09128

19Improving Adversarial Robustness via Channel-wise Activation SuppressingICLR 2021Ashkan-----------https://arxiv.org/abs/2103.08307







Transformers21Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Yousef-----------https://arxiv.org/abs/2103.14030

22Medical Transformer: Gated Axial-Attention for Medical Image Segmentation
YousefGüven Erkayahttps://arxiv.org/abs/2102.10662

23Vision Transformers for Dense Prediction
YousefMei-Ju Suhttps://arxiv.org/abs/2103.13413

24Automated Radiology Report Generation using Conditioned TransformersInformatics in Medicine Unlocked 2021Matthias-----------https://www.sciencedirect.com/science/article/pii/S2352914821000472







Graphs25Multi-Label Graph Convolutional Network Representation LearningIEEE Transactions on Big Data (TBD) 2020MahsaZhuoling Lihttps://arxiv.org/pdf/1912.11757.pdf

26Fast vertex-based graph convolutional neural network and its application to brain imagesNeurocomputing 2021Mahsa-----------https://www.sciencedirect.com/science/article/abs/pii/S0925231220320099

27Robust Graph Convolutional Networks Against Adversarial AttacksACM SIGKDD International Conference on Knowledge Discovery & Data Mining.AneesCarl Alexander Noackhttp://119.28.72.117/papers/RGCN.pdf

28Recovering Brain Structural Connectivity from Functional Connectivity via Multi-GCN Based Generative Adversarial NetworkMICCAI 2020Anees

Ayhan Can Erdur

https://link.springer.com/chapter/10.1007/978-3-030-59728-3_6


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.




  • Keine Stichwörter