DAGM GCPR | 2023
DAGM German Conference on Pattern Recognition, Heidelberg
Oral Sessions
| ID | Paper Title | Authors |
|---|---|---|
| 044 | Score-Based Generative Models for Medical Image Segmentation using Signed Distance Functions | Lea Bogensperger; Dominik Narnhofer; Filip Ilic; Thomas Pock |
| 107 | Best Practices in Active Learning for Semantic Segmentation | Sudhanshu Mittal; Joshua Niemeijer; Jörg P. Schäfer; Thomas Brox |
| 094 | DeViL: Decoding Vision features into Language | Meghal Dani; Isabel Rio-Torto; Stephan Alaniz; Zeynep Akata |
| 069 | Simplified Concrete Dropout - Improving the Generation of Attribution Masks for Fine-grained Classification | Dimitri Korsch; Maha Shadaydeh; Joachim Denzler |
| 052 | Underwater multiview stereo using axial camera models | Felix Seegräber; Patricia Schöntag; Felix Woelk; Kevin Koeser |
| 058 | DustNet: Attention to Dust | Andreas Michel; Martin Weinmann; Fabian Schenkel; tomas gomez; Mark Falvey; Rainer Schmitz; Wolfgang Middelmann; Stefan Hinz |
| 010 | LMD: Light-weight Prediction Quality Estimation for Object Detection in Lidar Point Clouds | Tobias Riedlinger; Marius Schubert; Sarina Penquitt; Jan Marcel Kezmann; Pascal Colling; Karsten Kahl; Lutz Roese-Koerner; Michael Arnold; Urs Zimmermann; Matthias Rottmann |
| 029 | A Network Analysis for Correspondence Learning via Linearly-Embedded Functions | Sharik Shabir Siddiqi; Zorah Laehner |
| 030 | Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks | Marvin Schmitt; Paul-Christian Bürkner; Ullrich Köthe; Stefan T. Radev |
| 084 | COOLer: Class-Incremental Learning for Appearance-Based Multiple Object Tracking | Zhizheng Liu; Mattia Segù; Fisher Yu |
| 064 | An Evaluation of Zero-Cost Proxies - from Neural Architecture Performance Prediction to Model Robustness | Jovita Lukasik; Michael Moeller; Margret Keuper |
| 125 (Nectar) | Open-Vocabulary Attribute Detection | Maria A Bravo; Sudhanshu Mittal; Simon Ging; Thomas Brox |
| 145 (Nectar) | FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods | Robin Hesse; Simone Schaub-Meyer; Stefan Roth |
| 119 (Nectar) | Efficient Video Prediction via Sparsely Conditioned Flow Matching | Aram Davtyan; Sepehr Sameni; Paolo Favaro |
Poster Session 1 (Wednesday 20.9, 14:50 – 16:20)
| ID | Paper Title | Authors |
|---|---|---|
| 001 (Nectar) | Conjugate Product Graphs for Globally Optimal 2D-3D Shape Matching | Paul Roetzer; Zorah Laehner; Florian Bernard |
| 012 (Nectar) | Neural Puppeteer: Keypoint-Based Neural Rendering of Dynamic Shapes | Simon Giebenhain; Urs Waldmann; Ole Johannsen; Bastian Goldluecke |
| 080 (Nectar) | Positive Difference Distribution for Image Outlier Detection using Normalizing Flows and Contrastive Data | Robert Schmier; Ullrich Köthe; Christoph-Nikolas Straehle |
| 082 (Nectar) | Automated Detection of Label Errors in Semantic Segmentation Datasets via Deep Learning and Uncertainty Quantification | Matthias Rottmann; Marco Reese |
| 114 (Nectar) | Capturing Shape Information With Multi-Scale Topological Loss Terms for 3D Reconstruction | Dominik Waibel; Scott Atwell; Matthias Meier; Carsten Marr; Bastian A Rieck |
| 116 (Nectar) | Unsupervised Learning of Robust Spectral Shape Matching | Dongliang Cao; Paul Roetzer; Florian Bernard |
| 121 (Nectar) | KOALA: A Kalman Optimization Algorithm with Loss Adaptivity | Aram Davtyan; Sepehr Sameni; Llukman Cerkezi; Givi Meishvili; Adam Bielski; Paolo Favaro |
| 126 (Nectar) | Weakly-Supervised Domain Adaptive Semantic Segmentation with Prototypical Contrastive Learning | Anurag Das; Yongqin Xian; Dengxin Dai; Bernt Schiele |
| 128 (Nectar) | Is one annotation enough? - A data-centric image classification benchmark for noisy and ambiguous label estimation | Lars Schmarje; Vasco Grossmann; Claudius Zelenka; Reinhard Koch |
| 130 (Nectar) | POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning | Frederik Schubert; Carolin Benjamins; Sebastian Döhler; Bodo Rosenhahn; Marius Lindauer |
| 136 (Nectar) | From t-SNE to UMAP with contrastive learning | Sebastian Damrich; Jan Niklas Böhm; Fred Hamprecht; Dmitry Kobak |
| 141 (Nectar) | Finding Competence Regions in Domain Generalization | Jens Müller; Stefan T. Radev; Robert Schmier; Felix Draxler; Carsten Rother; Ullrich Köthe |
| 019 (Nectar) | FrequencyLowCut Pooling - Plug & Play against Catastrophic Overfitting | Julia Grabinski; Steffen Jung; Janis Keuper; Margret Keuper |
| 096 (Nectar) | Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors | Tobias Riedlinger; Matthias Rottmann; Marius Schubert; Hanno Gottschalk |
| 117 (Nectar) | Representation Learning by Detecting Incorrect Location Embeddings | Sepehr Sameni; Simon Jenni; Paolo Favaro |
| 122 (Nectar) | Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability | Svetlana Pavlitska; Christian Hubschneider; Lukas Struppek; Marius Zöllner |
| 131 (Nectar) | Estimating the intrinsic dimensionality using Normalizing Flows | Christian Horvat; Jean-Pascal Pfister |
| 133 (Nectar) | TarViS: A Unified Approach for Target-based Video Segmentation | Ali Athar; Alexander Hermans; Jonathon Luiten; Deva Ramanan; Bastian Leibe |
| 138 (Nectar) | In-Style: Unsupervised Text-Video Retrieval with Style Preservation | Nina Shvetsova; Anna Kukleva; Bernt Schiele; Hilde Kuehne |
| 142 (Nectar) | DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer | Amit Kumar Rana; Sabarinath Mahadevan; Alexander Hermans; Bastian Leibe |
| 147 (Nectar) | Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet | Yannic Neuhaus; Maximilian Augustin; Valentyn Boreiko; Matthias Hein |
| 151 (Nectar) | ILLUME: Rationalizing Vision-Language Models through Human Interactions | Manuel Brack; Patrick Schramowski; Bjoern Deiseroth; Kristian Kersting |
| 089 | Point2Vec for Self-Supervised Representation Learning on Point Clouds | Karim Abou Zeid; Jonas Schult; Alexander Hermans; Bastian Leibe |
| 085 | GenLayNeRF: Generalizable Layered Representations with 3D Model Alignment for Human View Synthesis | Youssef Abdelkareem; Shady Shehata; Fakhri Karray |
| 105 | Multiclass Alignment of Confidence and Certainty for Network Calibration | Vinith Kugathasan; Muhammad Haris Khan |
| 086 | Automatic Reverse Engineering: Creating computer-aided design (CAD) models from multi-view images | Henrik Jobczyk; Hanno Homann |
| 109 | Characterization of out-of-distribution samples from uncertainty maps using supervised machine learning | Lina E Budde; Dimitri Bulatov; Eva Strauss; Kevin Qiu; Dorota Iwaszczuk |
| 090 | Drawing the Same Bounding Box Twice? Coping Noisy Annotations in Object Detection with Repeated Labels | David Eike Tschirschwitz; Christian Benz; Morris Florek; Henrik Norderhus; Benno Stein; Volker Rodehorst |
| 111 | FullFormer: Generating Shapes Inside Shapes | Tejaswini Medi; Jawad Tayyub; Muhammad Sarmad; Frank Lindseth; Margret Keuper |
| 075 | Correlation Clustering of Bird Sounds | David Stein; Bjoern Andres |
| 024 | Zero-shot Translation of Attention Patterns in VQA Models to Natural Language | Leonard Salewski; A. Sophia Koepke; Hendrik P. A. Lensch; Zeynep Akata |
| 007 | HiFiHR: Enhancing 3D Hand Reconstruction from a Single Image via High-Fidelity Texture | Jiayin Zhu; Zhuoran Zhao; Linlin Yang; Angela Yao |
| 040 | A Trimodal Dataset: RGB, Thermal, and Depth for Human Segmentation and Temporal Action Detection | Christian Stippel; Thomas TH Heitzinger; Martin Kampel |
| 041 | RC-BEVFusion: A Plug-In Module for Radar-Camera Bird's Eye View Feature Fusion | Lukas Staecker; Shashank Mishra; Philipp Heidenreich; Jason Rambach; Didier Stricker |
| 053 | M(otion)-mode Based Prediction of Ejection Fraction using Echocardiograms | Ece Ozkan; Thomas M. Sutter; Yurong Hu; Sebastian Balzer; Julia Vogt |
| 067 | Improving Data Efficiency for Plant Cover Prediction with Label Interpolation and Monte-Carlo Cropping | Matthias Körschens; Solveig Franziska Bucher; Christine Römermann; Joachim Denzler |
| 057 | Beyond Debiasing: Actively Steering Feature Selection via Loss Regularization | Jan Blunk; Niklas Penzel; Paul Bodesheim; Joachim Denzler |
| 125 (Nectar) (Oral) | Open-Vocabulary Attribute Detection | Maria A Bravo; Sudhanshu Mittal; Simon Ging; Thomas Brox |
| 094 (Oral) | DeViL: Decoding Vision features into Language | Meghal Dani; Isabel Rio-Torto; Stephan Alaniz; Zeynep Akata |
Poster Session 2 (Thursday 21.9, 14:30 – 16:00)
| ID | Paper Title | Authors |
|---|---|---|
| 003 (Nectar) | CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters | Paul Gavrikov; Janis Keuper |
| 049 (Nectar) | Superadditivity and Convex Optimization for Globally Optimal Cell Segmentation Using Deformable Shape Models | Leonid Kostrykin; Karl Rohr |
| 081 (Nectar) | UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GAN | Philipp Oberdiek; Gernot A. Fink; Matthias Rottmann |
| 115 (Nectar) | Topological Singularity Detection at Multiple Scales | Julius von Rohrscheidt; Bastian A Rieck |
| 120 (Nectar) | Controllable Video Generation Through Global and Local Motion Dynamics | Aram Davtyan; Paolo Favaro |
| 123 (Nectar) | Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences Using Transformer Networks | Haebom Lee; Christian Homeyer; Robert Herzog; Jan Rexilius; Carsten Rother |
| 124 (Nectar) | Beyond In-Domain Scenarios: Robust Density-Aware Calibration | Christian Tomani; Futa Kai Waseda; Yuesong Shen; Daniel Cremers |
| 129 (Nectar) | Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models | Patrick Schramowski; Manuel Brack; Bjoern Deiseroth; Kristian Kersting |
| 134 (Nectar) | SimNP: Learning Self-Similarity Priors Between Neural Points | Christopher Johannes Wewer; Eddy Ilg; Bernt Schiele; Jan E. Lenssen |
| 137 (Nectar) | Using Explanations to Guide Models | Sukrut Rao; Moritz Böhle; Amin Parchami-Araghi; Bernt Schiele |
| 143 (Nectar) | In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation | Julian Bitterwolf; Maximilian Mueller; Matthias Hein |
| 022 (Nectar) | Neural Architecture Design and Robustness: A Dataset | Steffen Jung; Jovita Lukasik; Margret Keuper |
| 113 (Nectar) | Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis | Lukas Struppek; Dominik Hintersdorf; Kristian Kersting |
| 118 (Nectar) | Spatio-Temporal Crop Aggregation for Video Representation Learning | Sepehr Sameni; Simon Jenni; Paolo Favaro |
| 127 (Nectar) | Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks | Dominik Schnaus; Jongseok Lee; Daniel Cremers; Rudolph Triebel |
| 132 (Nectar) | Spurious Valleys and Clustering Behavior of Neural Networks | Samuele Pollaci |
| 139 (Nectar) | Learning by Sorting: Self-supervised Learning with Group Ordering Constraints | Nina Shvetsova; Felix Petersen; Anna Kukleva; Bernt Schiele; Hilde Kuehne |
| 140 (Nectar) | Unscented Autoencoder | Faris Janjos; Lars Rosenbaum; Maxim Dolgov; Marius Zöllner |
| 146 (Nectar) | Learned Fourier Bases for Deep Set Feature Extractors in Automotive Reinforcement Learning | Maximilian B Schier; Christoph Reinders; Bodo Rosenhahn |
| 150 (Nectar) | Bridging the gap to real-world object-centric learning | Maximilian Seitzer; Andrii Zadaianchuk |
| 087 | Certified Robust Models with Slack Control and Large Lipschitz Constants | Max M Losch; David Stutz; Bernt Schiele; Mario Fritz |
| 095 | Self-Supervised Learning in Histopathology: New Perspectives for Prostate Cancer Grading | Markus Bauer; Christoph Augenstein |
| 099 | Parallax-aware Image Stitching based on Homographic Decomposition | Simon Seibt; Michael Arold; Bartosz von Rymon Lipinski; Uwe Wienkop; Marc Erich Latoschik |
| 112 | Airborne-Shadow: Towards Fine-Grained Shadow Detection in Aerial Imagery | Seyed Majid Azimi; Reza Bahmanyar |
| 098 | Learning Channel Importance for High Content Imaging with Interpretable Deep Input Channel Mixing | Daniel Siegismund; Mario Wieser; Stephan Heyse; Stephan Steigele |
| 102 | Text-to-feature diffusion for audio-visual few-shot learning | Otniel-Bogdan Mercea; Thomas Hummel; A. Sophia Koepke; Zeynep Akata |
| 108 | Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition | Katharina Prasse; Steffen Jung; Yuxuan Zhou; Margret Keuper |
| 071 | UGainS: Uncertainty Guided Anomaly Instance Segmentation | Alexey Nekrasov; Alexander Hermans; Lars Kuhnert; Bastian Leibe |
| 043 | Speeding Up Online Self-Supervised Learning by Exploiting Its Limitations | Sina Mokhtarzadeh Azar; Radu Timofte |
| 018 | Label Smarter, Not Harder: CleverLabel for Faster Annotation of Ambiguous Image Classification with Higher Quality | Lars Schmarje; Vasco Grossmann; Tim Michels; Jakob Nazarenus; Monty Santarossa; Claudius Zelenka; Reinhard Koch |
| 065 | MargCTGAN: A "Marginally" Better CTGAN for the Low Sample Regime | Tejumade Afonja; Dingfan Chen; Mario Fritz |
| 072 | Leveraging Bioclimatic Context for Supervised and Self-Supervised Land Cover Classification | Johannes Leonhardt; Lukas Drees; Jürgen Gall; Ribana Roscher |
| 048 | 3D Retinal Vessel Segmentation in OCTA Volumes: Annotated Dataset MORE3D and Hybrid U-Net with Flattening Transformation | Julian Kuhlmann; Kai Rothaus; Xiaoyi Jiang; Henrik Faatz; Daniel Pauleikhoff; Matthias Gutfleisch |
| 016 | Adversarial Perturbations Straight on JPEG Coefficients | Kolja Luca Sielmann; Peer Stelldinger |
| 107 (Oral) | Best Practices in Active Learning for Semantic Segmentation | Sudhanshu Mittal; Joshua Niemeijer; Jörg P. Schäfer; Thomas Brox |
| 029 (Oral) | A Network Analysis for Correspondence Learning via Linearly-Embedded Functions | Sharik Shabir Siddiqi; Zorah Laehner |