Instructors: Prof. Dr. Nassir NavabDr. Shahrooz Faghih Roohi,  Ashkan Khakzar, Azade Farshad, Yousef Yeganeh


Time: TBA

Registration

Announcements

  • The presentation and blogpost guidelines are available here: Guide_DLMA SS2022.pdf 
  • The preliminary meeting slides can be found here: DLMASS22.pdf
  • The preliminary meeting is scheduled for Feb 3, 10:30 (Zoom link is visible on TUMonline).

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 topic from the list provided by course organizers. The students should read the proposed sample papers by the tutors, find the topic-related articles, summarize and compare them in their presentation and blogpost:

  • Presentation: The selected paper is presented to the other participants (Maximum 25 minutes presentation, 10 minutes questions). You can use the CAMP templates for PowerPoint TUM-Template.pptx.
  • Blog Post: A blog post of 2000-2500 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 first draft of the blog post one week before your presentation session. However, you would have time to modify it until the last session, July 28th. You should also submit the presentation one day right after your presentation session.

Schedule

TBA

DateSession: TopicsSlidesStudents
12.05Preliminary Meeting

09.06

Few-shot Image Synthesis

Image-to-Image Translation


Juan Carlos Climent Pardo

Wang, Yihao

23.06

Vision Transformers

Transformers for Segmentation

Medical Visual Question Answering (VQA)


Demir, Ufuk

Ganß, Marcel

Demmel, Julia

30.06

Semi/self-supervised Methods for Vessel Segmentation

Task Modelling in Meta-learning

Unsupervised Domain Adaptation for Segmentation


Hasny, Marta

Chenyang Li

Fabian Scherer

07.07

Semi-Supervised Learning /Semi-Supervised Federated Learning

Contrastive Learning/Trends in Self-Supervised Learning

Unsupervised Anomaly Detection


Młynarczyk, Dominika

Schreiber, Manuel

Trotman, Rachelle

14.07

Neural Network Robustness (adversarial examples)

Neural Network Verification


Çelik, Furkan

Engstler, Paul

21.07

Shape-aware semi-supervised image segmentation

Shape Completion

Trends in Data Augmentation


Capelle, Finn

Konov Mikhail

Salah, Skander

28.07

Deep Learning-based medical image registration

Representation Learning using Generative Models

implicit neural representations with deformation



Zhang, Zichen

Bohosyan, Aleks

Bou Orm, Ali

List of Topics and Material

The proposed papers for each topic in this course are usually 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 

NoTopicSample PapersJournal/ ConferenceTutorStudentLink
1Shape-aware semi-supervised image segmentationSimCVD: Simple Contrastive Voxel-Wise
Representation Distillation for Semi-Supervised
Medical Image Segmentation
TMI 2020Capelle, Finnhttps://ieeexplore.ieee.org/abstract/document/9740182
3D Graph-S2Net: Shape-Aware Self-ensembling Network for Semi-supervised Segmentation with Bilateral Graph ConvolutionMICCAI 2021https://link.springer.com/chapter/10.1007/978-3-030-87196-3_39
2

Few-shot Image Synthesis

Towards faster and stabilized gan training for high-fidelity few-shot image synthesisICLR 2020Juan Carlos Climent Pardohttps://openreview.net/forum?id=1Fqg133qRaI
One-Shot GAN: Learning To Generate Samples From Single Images and VideosCVPR 2021

https://openaccess.thecvf.com/content/CVPR2021W/LLID/html/Sushko_One-Shot_GAN_Learning_To_Generate_Samples_From_Single_Images_and_CVPRW_2021_paper.html

3Semi/self-supervised Methods for Vessel SegmentationDual-consistency semi-supervision combined with self-supervision for vessel segmentation in retinal OCTA imagesBiomedical Optics Express 2022Faghihroohi, Shahrooz Hasny, Martahttps://opg.optica.org/boe/fulltext.cfm?uri=boe-13-5-2824&id=471607
LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel SegmentationMICCAI 2021https://link.springer.com/chapter/10.1007/978-3-030-87193-2_49
4Shape CompletionGRNet: Gridding Residual Network for Dense Point Cloud CompletionECCV 2020Konov Mikhailhttps://arxiv.org/pdf/2006.03761.pdf
AutoSDF: Shape Priors for 3D Completion, Reconstruction and GenerationCVPR 2022https://arxiv.org/pdf/2203.09516.pdf
5Semi-Supervised Learning /Semi-Supervised Federated Learning A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained ClassificationCVPR 2021Młynarczyk, Dominika

https://openaccess.thecvf.com/content/CVPR2021/papers/Su_A_Realistic_Evaluation_of_Semi-Supervised_Learning_for_Fine-Grained_Classification_CVPR_2021_paper.pdf

Semi-supervised Medical Image Segmentation via a Tripled-uncertainty Guided Mean Teacher Model with Contrastive LearningMedIA 2022https://www.sciencedirect.com/science/article/abs/pii/S1361841522000925
6Deep Learning based medical image registrationOrientation Estimation of Abdominal Ultrasound Images with Multi-Hypotheses NetworksMIDL 2022Zhang, Zichenhttps://openreview.net/pdf?id=1gsauv2B7Ar
Cross-Modal Attention for MRI and Ultrasound Volume RegistrationMICCAI 2021https://link.springer.com/content/pdf/10.1007/978-3-030-87202-1_7.pdf
7Trends in Data AugmentationFast AdvPropICLR2022Yeganeh, Y. M. Salah, Skanderhttps://openreview.net/forum?id=hcoswsDHNAW
SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question AnsweringCVPR2022https://arxiv.org/abs/2204.02285
8Contrastive Learning/Trends in Self-Supervised LearningVICReg: Variance-Invariance-Covariance Regularization for Self-Supervised LearningNeurIPS 2021Schreiber, Manuelhttps://arxiv.org/abs/2105.04906
Masked Siamese Networks for Label-Efficient LearningCVPR2022https://arxiv.org/abs/2204.07141
9Self-Supervised Learnig with False Negative SelectionSAM: Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological ImagesTMI 2021Bdair, Tariq Not Assigned

https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9760421&casa_token=eWq-YFK9AJAAAAAA:PeRS4-wXOQMLf4hBMuY3rEbW6S8ZYJW7MxchseXpfotxJvlG9TI8kxAOlqX9w0hGxb7L_oX_-Q8

Boosting Contrastive Self-Supervised Learning with False Negative CancellationWACV 2022

https://openaccess.thecvf.com/content/WACV2022/papers/Huynh_Boosting_Contrastive_Self-Supervised_Learning_With_False_Negative_Cancellation_WACV_2022_paper.pdf

10Unsupervised Anomaly DetectionUnsupervised Anomaly Detection in Medical Images with a Memory-augmented Multi-level Cross-attentional Masked AutoencoderCVPR 2022Trotman, Rachellehttps://arxiv.org/pdf/2201.13271v1.pdf
StRegA: Unsupervised Anomaly Detection in Brain MRIs using a Compact Context-encoding Variational Autoencoder CVPR 2022https://arxiv.org/pdf/2203.11725v1.pdf
11Transformers for SegmentationUnsupervised Anomaly Detection in Medical Images with a Memory-augmented Multi-level Cross-attentional Masked AutoencoderICCV2021Ganß, Marcelhttps://arxiv.org/abs/2203.11725
StRegA: Unsupervised Anomaly Detection in Brain MRIs using a Compact Context-encoding Variational AutoencoderCVPR2021https://arxiv.org/abs/2201.13271
12Neural Network Robustness (adversarial examples)Adversarial Examples Are Not Bugs, They Are FeaturesICLR 2019Khakzar, Ashkan Çelik, Furkanhttps://arxiv.org/abs/1905.02175
Reading Race: AI Recognises Patient's Racial Identity In Medical Images
https://arxiv.org/abs/2107.10356
13Neural Network VerificationBias Field Robustness Verification of Large Neural Image ClassifiersBMVC 2021Khakzar, Ashkan Engstler, Paulhttps://www.bmvc2021-virtualconference.com/assets/papers/1291.pdf
Efficient Neural Network Verification via Adaptive Refinement and Adversarial SearchECAI 2020https://ebooks.iospress.nl/doi/10.3233/FAIA200385
14Task Modelling in Meta-learningMeta-Learning with Fewer Tasks through Task InterpolationICLR 2022Farshad, Azade Chenyang Lihttps://arxiv.org/pdf/2106.02695.pdf
Task Relatedness-Based Generalization Bounds for Meta LearningICLR 2022https://openreview.net/pdf?id=A3HHaEdqAJL
15Knowledge Distillation in Meta-learning (Optional)BERT Learns to Teach: Knowledge Distillation with Meta LearningACL 2022Farshad, Azade Not Assignedhttps://arxiv.org/pdf/2106.04570.pdf
Online Hyperparameter Meta-Learning with Hypergradient DistillationICLR 2022https://arxiv.org/pdf/2110.02508.pdf
16Representation Learning using Generative ModelsShape your Space: A Gaussian Mixture Regularization Approach to Deterministic AutoencodersNeurIPS 2021Farshad, Azade Bohosyan, Aleks 

https://proceedings.neurips.cc/paper/2021/file/3c057cb2b41f22c0e740974d7a428918-Paper.pdf

GENERATIVE MODELS AS A DATA SOURCE FOR MULTIVIEW REPRESENTATION LEARNINGICLR 2022https://arxiv.org/pdf/2106.05258.pdf
17Vision TransformersAn Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleICLR 2021Velikova, Yordanka Demir, Ufukhttps://arxiv.org/pdf/2010.11929.pdf
Masked-attention Mask Transformer for Universal Image SegmentationCVPR 2022https://arxiv.org/pdf/2112.01527v2.pdf
18Image-to-Image TranslationThe Spatially-Correlative Loss for Various Image Translation Tasks (LSeSim )ICCV 2021Wang, Yihao https://arxiv.org/pdf/2104.00854.pdf
Contrastive learning for un-paired image-to-image translationECCV 2020https://arxiv.org/pdf/2007.15651.pdf
19Medical Visual Question Answering (VQA)MMBERT: Multimodal BERT Pretraining for Improved Medical VQAISBI 2021Keicher, Matthias Demmel, Julia

https://ieeexplore.ieee.org/abstract/document/9434063?casa_token=tokBDN5DmREAAAAA:XMajOpu-24mZxOsRMiIcS1pCkjHMn8PIpNUk_xcFfjUr7LACKjgFWPjGw4GPb_ZUQLiYqC1M

Vision-Language Transformer for Interpretable Pathology Visual Question AnsweringIEEE Journal of Biomedical and Health Informatics

https://ieeexplore.ieee.org/abstract/document/9745795?casa_token=2MNEdPL-ItgAAAAA:P5PJdPxjj1vAHunGCSBekU2vQkvLIBhM-xcg0PGQt_5A_Qkv0pkGYH7ohIeB90x9TYzFOaN-

20implicit neural representations with deformationNerfies: Deformable Neural Radiance FieldsICCV 2021Bou Orm, Alihttps://arxiv.org/pdf/2011.12948
D-NeRF: Neural Radiance Fields for Dynamic ScenesCVPR 2021https://arxiv.org/abs/2011.13961
21Unsupervised Domain Adaptation for SegmentationSelf-Attentive Spatial Adaptive Normalization for Cross-Modality Domain AdaptationTMI 2021Fabian Schererhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9380742
DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic SegmentationCVPR 2021https://arxiv.org/pdf/2104.10834.pdf


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

2 Comments

  1. Hello, in the pdf about the structure of the Blog Post (https://wiki.tum.de/download/attachments/1046907253/Guide_DLMA%20SS2022.pdf?version=1&modificationDate=1653688942210&api=v2), something is broken. The sentence "It should summarize the topic with high emphasis on the" just stops without telling me on what I should emphasis (big grin)

    Could you please correct this.

    1. Hi Fabian, thanks for mentioning that! I forgot to complete this part. The emphasis would be on: 

      Problem Statement / Big picture

      Methodology of other works related to the topics

      Important Results that may compare the state-of-the-art related to the topic.