Page tree
Skip to end of metadata
Go to start of metadata


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


Time: TBA

Registration

Announcements

  • The preliminary meeting slides can be found here: DLMASws21-22.pdf
  • The preliminary meeting is scheduled for July 7th, 16:30 (Zoom link is visible on TUMonline).
  • 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

TBA

DateSession: TopicSlidesStudents
07.06Preliminary MeetingDLMASws21-22.pdf
TBA


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 generation1Semi-supervised Medical Image Segmentation through Dual-task ConsistencyAAAI 2021Shahrooz
https://ojs.aaai.org/index.php/AAAI/article/view/17066

2Exploring and Distilling Posterior and Prior Knowledge for Radiology Report GenerationCVPR 2021Matthias

https://openaccess.thecvf.com/content/CVPR2021/html/Liu_Exploring_and_Distilling_Posterior_and_Prior_Knowledge_for_Radiology_Report_CVPR_2021_paper.html


3Anatomy-Constrained Contrastive Learning for Synthetic Segmentation Without Ground-TruthMICCAI 2021Mehdi
https://link.springer.com/chapter/10.1007%2F978-3-030-87193-2_5

4Comparison of thyroid segmentation techniques for 3D ultrasoundMedical Imaging 2017: Image ProcessingChrissi, Lennart, Matthias
https://www.var.ovgu.de/pub/2017_Wunderling_SPIE_comparison-thyroid-segmentation-SPIE-submission.pdf
Unsupervised/Semi-supervised/Self-supervised learning5Unpaired Training of Deep Learning tMRA for Flexible Spatio-Temporal ResolutionTMI 2021Shahrooz
https://ieeexplore.ieee.org/abstract/document/9195022

6IN DEFENSE OF PSEUDO-LABELING: AN UNCERTAINTY-AWARE PSEUDO-LABEL SELECTION FRAMEWORK FOR SEMI-SUPERVISED LEARNINGICLR 2021Tariq
https://openreview.net/pdf?id=-ODN6SbiUU

7Local plasticity rules can learn deep representations using self-supervised contrastive predictionsNeurIPS 2021Ashkan
https://arxiv.org/abs/2010.08262

8Prototypical Contrastive Learning of Unsupervised RepresentationsICLR 2021Tariq
https://arxiv.org/pdf/2101.06329v3.pdf

9Improving Contrastive Learning by Visualizing Feature TransformationICCV 2021Yousef

https://openaccess.thecvf.com/content/ICCV2021/papers/Zhu_Improving_Contrastive_Learning_by_Visualizing_Feature_Transformation_ICCV_2021_paper.pdf


10How Well Do Self-Supervised Models Transfer?CVPR 2021Yousef

http://openaccess.thecvf.com//content/CVPR2021/papers/Ericsson_How_Well_Do_Self-Supervised_Models_Transfer_CVPR_2021_paper.pdf


11Dense Contrastive Learning for Self-Supervised Visual Pre-TrainingCVPR 2021Yousef

http://openaccess.thecvf.com//content/CVPR2021/papers/Wang_Dense_Contrastive_Learning_for_Self-Supervised_Visual_Pre-Training_CVPR_2021_paper.pdf


12Object-aware Contrastive Learning for Debiased Scene RepresentationarXive 2021 (Google)Yousef
https://arxiv.org/pdf/2108.00049v1.pdf
Data-Efficient DL, Representation Learning13Public Covid-19 X-ray datasets and their impact on model bias – A systematic review of a significant problemMedIA 2021Ashkan
https://www.medrxiv.org/content/10.1101/2021.02.15.21251775v1.full

14Shallow Bayesian Meta Learning for Real-World Few-Shot RecognitionICCV 2021Azade
https://arxiv.org/pdf/2101.02833.pdf

15Exploring Simple Siamese Representation LearningCVPR 2021Azade

https://openaccess.thecvf.com/content/CVPR2021/papers/Chen_Exploring_Simple_Siamese_Representation_Learning_CVPR_2021_paper.pdf


16Conditional Deformable Image Registration with Convolutional Neural NetworkMICCAI 2021Anees

Reliable AI (Interpretability, Uncertainty, robustness)17Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their ExplanationsCVPR 2021Ashkan
https://arxiv.org/abs/2011.12854

18Propagating Uncertainty Across Cascaded Medical Imaging Tasks For Improved Deep Learning InferenceTMI 2021Shahrooz
https://ieeexplore.ieee.org/abstract/document/9541203

19How Well do Feature Visualizations Support Causal Understanding of CNN Activations?NeurIPS 2021Ashkan


20Generative Classifiers as a Basis for Trustworthy Computer VisionCVPR 2021Heiko

https://openaccess.thecvf.com/content/CVPR2021/papers/Mackowiak_Generative_Classifiers_as_a_Basis_for_Trustworthy_Image_Classification_CVPR_2021_paper.pdf

Transformers21DEFORMABLE DETR: DEFORMABLE TRANSFORMERS FOR END-TO-END OBJECT DETECTIONICLR2021Farid
https://arxiv.org/pdf/2010.04159.pdf

22TransPath: Transformer-Based Self-supervised Learning for Histopathological Image ClassificationMICCAI 2021Anees


23Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with TransformersCVPR 2021Yousef

http://openaccess.thecvf.com//content/CVPR2021/papers/Zheng_Rethinking_Semantic_Segmentation_From_a_Sequence-to-Sequence_Perspective_With_Transformers_CVPR_2021_paper.pdf


24Transformer Interpretability Beyond Attention VisualizationCVPR 2021Yousef

http://openaccess.thecvf.com//content/CVPR2021/papers/Chefer_Transformer_Interpretability_Beyond_Attention_Visualization_CVPR_2021_paper.pdf

Graphs25DualGraph: A graph-based method for reasoning about label noiseCVPR 2021Mahsa

https://openaccess.thecvf.com/content/CVPR2021/papers/Zhang_DualGraph_A_Graph-Based_Method_for_Reasoning_About_Label_Noise_CVPR_2021_paper.pdf


26ON GRAPH NEURAL NETWORKS VERSUS GRAPH AUGMENTED MLPSICLR 2021Mahsa
https://openreview.net/pdf?id=tiqI7w64JG2

27Heterogeneous Graph TransformerACM DLAnees
https://arxiv.org/abs/2003.01332
Other28pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image SynthesisCVPR 2021Farid

https://openaccess.thecvf.com/content/CVPR2021/papers/Chan_Pi-GAN_Periodic_Implicit_Generative_Adversarial_Networks_for_3D-Aware_Image_Synthesis_CVPR_2021_paper.pdf


29Neural Deformation Graphs for Globally-consistent Non-rigid ReconstructionCVPR 2021Farid

https://openaccess.thecvf.com/content/CVPR2021/papers/Bozic_Neural_Deformation_Graphs_for_Globally-Consistent_Non-Rigid_Reconstruction_CVPR_2021_paper.pdf


30Deep learning on ultrasound images of thyroid nodulesBiocybernetics and Biomedical EngineeringChrissi, Lennart, Matthias
https://www.sciencedirect.com/science/article/abs/pii/S0208521621000152

31Bayesflow: Learning Complex Stochastic Models with Invertible Neural NetworksIEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2020Heiko
https://ieeexplore.ieee.org/document/9298920

32Model-Contrastive Federated LearningCVPR 2021Yousef

http://openaccess.thecvf.com//content/CVPR2021/papers/Li_Model-Contrastive_Federated_Learning_CVPR_2021_paper.pdf


33Autonomic Robotic Ultrasound Imaging System Based on Reinforcement LearningIEEE Transactions on Biomedical EngineeringMaria
https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=10


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