adamkortylewski.com Open in urlscan Pro
85.13.162.145  Public Scan

Form analysis
0 forms found in the DOM

Text Content

ADAM KORTYLEWSKI, PHD

I am a research group leader at MPI-Informatics leading the "Generative Vision"
research group and working closely with Prof. Christian Theobalt. Before that I
was a postdoctoral researcher at Johns Hopkins University working with Prof.
Alan Yuille and a PhD student and postdoctoral researcher at the University of
Basel working with Prof. Thomas Vetter.

I research generative computer vision models that perform visual recognition
through analysis-by-synthesis. My work demonstrates that the integration of deep
learning with generative vision models enables an enhanced robustness in
out-of-distribution scenarios, a more efficient learning and an inherent
multi-tasking.


RECENT NEWS

 * Jan. 2022: I started my own research group at MPI-Informatics! (website
   coming soon)
 * Dec. 2021: Our paper on Transformers for Fine-Grained Recognition was
   accepted @ AAAI.
 * Sep. 2021: First paper as a senior author 🎉:
   Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of
   3D Pose @ NeurIPS.
 * Jul. 2021: Our paper on Signed Distance Functions for Articulated Shape
   Representation was accepted @ ICCV.
 * May. 2021: I will be a panelist at the Workshop on Security and Safety in
   Machine Learning Systems @ ICLR.
 * May. 2021: We present recent works at the Workshop on Generalization beyond
   the training distribution @ ICLR.
 * Apr. 2021: We organize the 2nd Workshop on Adversarial Robustness in the Real
   World @ ICCV.
 * Mar. 2021: Our paper on Reasoning about Multi-Object Occlusion for Instance
   Segmentation was accepted @ CVPR.
 * Jan. 2021: Our paper on Neural Mesh Models was accepted @ ICLR.
 * Jan. 2021: Our paper on Robustness of Compositional Representations was
   presented @ CISS.




PUBLICATIONS

(*) indicates joint senior authorship



TransFG: A Transformer Architecture for Fine-grained Recognition
Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai,
Changhu Wang, Alan Yuille
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)
[ PDF ] [ CODE ] Neural View Synthesis and Matching for Semi-Supervised Few-Shot
Learning of 3D Pose
Angtian Wang, Shenxiao Mei, Alan Yuille, Adam Kortylewski
Advances in Neural Information Processing Systems (NeurIPS) 2021
[ PDF ] [ CODE ] A-SDF: Learning Disentangled Signed Distance Functions for
Articulated Shape Representation
Jiteng Mu, Weichao Qiu, Adam Kortylewski, Alan Yuille, Nuno Vasconcelos,
Xiaolong Wang
Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2021
[ PDF ] [ CODE ] [VIDEO] Robust Instance Segmentation through Reasoning about
Multi-Object Occlusion
Xiaoding Yuan, Adam Kortylewski, Alan Yuille
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
(CVPR) 2021
[ PDF ] [ CODE ] NeMo: Neural Mesh Models of Contrastive Features for Robust 3D
Pose Estimation
Angtian Wang, Adam Kortylewski, Alan Yuille
International Conference on Learning Representations (ICLR) 2021
[ PDF ] [ CODE ] [ VIDEO ] Compositional Generative Networks and Robustness to
Perceptible Image Changes
Adam Kortylewski, Ju He, Qing Liu, Christian Cosgrove, Chenglin Yang, Alan
Yuille
55th Annual Conference on Information Sciences and Systems (CISS) 2021
[ PDF ] Compositional Convolutional Neural Networks: A Robust and Interpretable
Model for Object Recognition under Occlusion
Adam Kortylewski, Qing Liu, Angtian Wang, Yihong Sun, Alan Yuille
International Journal of Computer Vision (IJCV) 2020
[ PDF ] [ CODE ] PatchAttack: A Black-box Texture-based Attack with
Reinforcement Learning
Chenglin Yang, Adam Kortylewski, Cihang Xie, Yinzhi Cao, Alan Yuille
Proceedings of the European Conference on Computer Vision (ECCV) 2020
[ PDF ] [ CODE ] Robust Object Detection under Occlusion with Context-Aware
CompositionalNets
Angtian Wang, Yihong Sun, Adam Kortylewski(*), Alan Yuille(*)
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
(CVPR) 2020
[ PDF ] Compositional Convolutional Neural Networks: A Deep Architecture with
Innate Robustness to Partial Occlusion
Adam Kortylewski, Ju He, Qing Liu, Alan Yuille
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
(CVPR) 2020
[ PDF ] [ Supplementary ] [ CODE ] [ VIDEO ] Localizing Occluders with
Compositional Convolutional Networks
Adam Kortylewski, Qing Liu, Huiyu Wang, Zhishuai Zhang, Alan Yuille
Advances in Neural Information Processing Systems 2019, Context and
Compositionality in Biological and Artificial Neural Systems Workshop.
IEEE International Conference on Computer Vision (ICCV) 2019, Neural Architects
Workshop
[ PDF ] TDAPNet: Prototype Network with Recurrent Top-Down Attention for Robust
Object Classification under Partial Occlusion
Mingqing Xiao, Adam Kortylewski, Ruihai Wu, Siyuan Qiao, Wei Shen, Alan Yuille.
ECCV 2020 Workshop on Visual Inductive Priors for Data-Efficient Deep Learning
[ PDF ] 3D Morphable Face Models - Past, Present and Future
Bernhard Egger, William A.P Smith, Ayush Tewari, Stefanie Wuhrer, Michael
Zollhoefer, Thabo Beeler, Florian Bernhard, Timo Bolkart, Adam Kortylewski, Sami
Romdhani, Christian Theobalt, Volker Blanz, Thomas Vetter.
ACM Transactions on Graphics (TOG)
[ PDF ] Combining Compositional Models and Deep Networks For Robust Object
Classification under Occlusion
Adam Kortylewski, Qing Liu, Huiyu Wang, Zhishuai Zhang, Alan Yuille.
IEEE Winter Conference on Applications of Computer Vision (WACV) 2020.
Spotlight
[ PDF ] [ Slides ] [ Poster ] [ Video ] Greedy Structure Learning of
Hierarchical Compositional Models
Adam Kortylewski, Clemens Blumer, Aleksander Wieczorek, Mario Wieser, Sonali
Parbhoo, Andreas Morel-Forster, Volker Roth, Thomas Vetter.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
(CVPR) 2019
[ PDF ] [ Poster ] Analyzing and Reducing the Damage of Dataset Bias to Face
Recognition With Synthetic Data
Adam Kortylewski, Bernhard Egger, Andreas Schneider, Thomas Gerig, Andreas
Morel-Forster, Thomas Vetter.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Workshops 2019
2nd Workshop on Bias Estimation in Face Analytics (BEFA)
Oral, Best Paper
[ PDF ] [ PPT ] [ Poster ] SkelNetOn 2019 Dataset and Challenge on Deep Learning
for Geometric Shape Understanding
Ilke Demir, Camilla Hahn, Kathryn Leonard, Geraldine Morin, Dana Rahbani, Athina
Panotopoulou, Amelie Fondevilla, Elena Balashova, Bastien Durix, Adam
Kortylewski.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Workshops 2019
Deep Learning for Geometric Shape Understanding Workshop
[ PDF ] Informed MCMC with Bayesian Neural Networks for Facial Image Analysis
Adam Kortylewski, Mario Wieser, Andreas Morel-Forster, Aleksander Wieczorek,
Sonali Parbhoo, Volker Roth, Thomas Vetter.
NeurIPS 2018 - Bayesian Deep Learning Workshop
[ PDF ][ Poster ] Training Deep Face Recognition Systems with Synthetic Data
Adam Kortylewski, Andreas Schneider, Thomas Gerig, Bernhard Egger, Andreas
Morel-Forster, Thomas Vetter.
Technical Report, arXiv, 2018
[ PDF ] [ Code ] Occlusion-aware 3D Morphable Models and an Illumination Prior
for Face Image Analysis
Bernhard Egger, Sandro Schönborn, Andreas Schneider, Adam Kortylewski, Andreas
Morel-Forster, Clemens Blumer and Thomas Vetter.
International Journal of Computer Vision (IJCV), 2018
[ PDF ] [ Code ] Empirically Analyzing the Effect of Dataset Biases on Deep Face
Recognition Systems
Adam Kortylewski, Bernhard Egger, Andreas Schneider, Thomas Gerig, Andreas
Forster, Thomas Vetter.
CVPR 2018 - 8th Workshop on Analysis and Modeling of Faces and Gestures (AMFG)
Oral
[ PDF ] [ Poster ] [ Code ] Model-based Image Analysis for Forensic Shoe Print
Recognition
Adam Kortylewski.
PhD Thesis, 2017
[ PDF ] [ PPT ] Probabilistic Compositional Active Basis Models for Robust
Pattern Recognition
Adam Kortylewski and Thomas Vetter.
BMVC 2016
[ PDF ] [ One Page Abstract ] [ Poster ] Unsupervised Footwear Impression
Analysis and Retrieval from Crime Scene Data
Adam Kortylewski, Thomas Albrecht and Thomas Vetter.
ACCV 2014 Workshops.
[ PDF ] [ Poster ]



INVITED TALKS

Robust Computer Vision through Neural Analysis-by-Synthesis with Compositional
Generative Networks
03/2021 MIT
[ PDF ]
Robust Object Recognition under Occlusion with Compositional Convolutional
Neural Networks
12/2019 National Institute of Standards & Techonolgy
[ PDF ]
A Generative Approach to Shape-based Image Analysis
01/2017 Johns Hopkins University
01/2017 National Institute of Standards & Techonolgy
02/2017 Michigan State University
02/2017 Iowa State University (Webinar)

[ PDF ] [ PPT ] [ WEBINAR ]



Advances in Automated Footwear Impression Analysis
10/2016 12th ENFSI Shoeprint and Toolmark Meeting , Vienna
[ PDF ] [ PPT ] Automated Footwear Impression Analysis and Retrieval Based on
Periodic Patterns
10/2014 11th ENFSI Shoeprint and Toolmark Meeting, Prague
[ PDF ] [ PPT ] An Automaed Pattern Recognition System For Shoe Tracks
06/2013 10th ENFSI Shoeprint and Toolmark Meeting, Bled
[ PDF ] [ PPT ]



MISC

Parametric Face Image Generator
A software for generating synthetic face images based on a 3D Morphable Face
Model.
[ Website ] Footwear Impression Database
A database for forensic footwear impression analysis.
[ Website ]



Generative Vision Research Group
Max Planck Institute for Informatics





Google Scholar
Github
Twitter
Youtube
LinkedIn