Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Adam Kortylewski

A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation


Apr 15, 2021
Jiteng Mu, Weichao Qiu, Adam Kortylewski, Alan Yuille, Nuno Vasconcelos, Xiaolong Wang

* Our project page is available at: https://jitengmu.github.io/A-SDF/ 

  Access Paper or Ask Questions

TransFG: A Transformer Architecture for Fine-grained Recognition


Mar 28, 2021
Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille

* Release official PyTorch implementation of the paper 

  Access Paper or Ask Questions

CGPart: A Part Segmentation Dataset Based on 3D Computer Graphics Models


Mar 25, 2021
Qing Liu, Adam Kortylewski, Zhishuai Zhang, Zizhang Li, Mengqi Guo, Qihao Liu, Xiaoding Yuan, Jiteng Mu, Weichao Qiu, Alan Yuille

* 18 pages, 10 figures 

  Access Paper or Ask Questions

Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping


Feb 22, 2021
Prakhar Kaushik, Alex Gain, Adam Kortylewski, Alan Yuille


  Access Paper or Ask Questions

NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation


Feb 04, 2021
Angtian Wang, Adam Kortylewski, Alan Yuille

* Accepted by ICLR 2021. Code is publicly available 

  Access Paper or Ask Questions

COMPAS: Representation Learning with Compositional Part Sharing for Few-Shot Classification


Jan 28, 2021
Ju He, Adam Kortylewski, Alan Yuille


  Access Paper or Ask Questions

Robust Instance Segmentation through Reasoning about Multi-Object Occlusion


Dec 03, 2020
Xiaoding Yuan, Adam Kortylewski, Yihong Sun, Alan Yuille


  Access Paper or Ask Questions

Robustness Out of the Box: Compositional Representations Naturally Defend Against Black-Box Patch Attacks


Dec 01, 2020
Christian Cosgrove, Adam Kortylewski, Chenglin Yang, Alan Yuille


  Access Paper or Ask Questions

Unsupervised Part Discovery via Feature Alignment


Dec 01, 2020
Mengqi Guo, Yutong Bai, Zhishuai Zhang, Adam Kortylewski, Alan Yuille

* 10 pages, 9 figures, submitted to CVPR 2021 

  Access Paper or Ask Questions

Weakly-Supervised Amodal Instance Segmentation with Compositional Priors


Oct 25, 2020
Yihong Sun, Adam Kortylewski, Alan Yuille


  Access Paper or Ask Questions

CoKe: Localized Contrastive Learning for Robust Keypoint Detection


Sep 30, 2020
Yutong Bai, Angtian Wang, Adam Kortylewski, Alan Yuille


  Access Paper or Ask Questions

Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion


Jun 28, 2020
Adam Kortylewski, Qing Liu, Angtian Wang, Yihong Sun, Alan Yuille


  Access Paper or Ask Questions

Robust Object Detection under Occlusion with Context-Aware CompositionalNets


May 30, 2020
Angtian Wang, Yihong Sun, Adam Kortylewski, Alan Yuille

* Accepted to CVPR 2020 

  Access Paper or Ask Questions

Robust Object Detection under Occlusion with \\Context-Aware CompositionalNets


May 24, 2020
Angtian Wang, Yihong Sun, Adam Kortylewski, Alan Yuille

* Accepted to CVPR 2020 

  Access Paper or Ask Questions

PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning


Apr 12, 2020
Chenglin Yang, Adam Kortylewski, Cihang Xie, Yinzhi Cao, Alan Yuille


  Access Paper or Ask Questions

Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion


Apr 03, 2020
Adam Kortylewski, Ju He, Qing Liu, Alan Yuille

* CVPR 2020; Code is available https://github.com/AdamKortylewski/CompositionalNets 

  Access Paper or Ask Questions

Localizing Occluders with Compositional Convolutional Networks


Nov 18, 2019
Adam Kortylewski, Qing Liu, Huiyu Wang, Zhishuai Zhang, Alan Yuille

* Presented at "NeurIPS 2019 workshop on Perception as generative reasoning" and "NeurIPS 2019 workshop on Context and Compositionality in Biological and Artificial Neural Systems". arXiv admin note: text overlap with arXiv:1905.11826 

  Access Paper or Ask Questions

TDAPNet: Prototype Network with Recurrent Top-Down Attention for Robust Object Classification under Partial Occlusion


Sep 09, 2019
Mingqing Xiao, Adam Kortylewski, Ruihai Wu, Siyuan Qiao, Wei Shen, Alan Yuille


  Access Paper or Ask Questions

3D Morphable Face Models -- Past, Present and Future


Sep 03, 2019
Bernhard Egger, William A. P. Smith, Ayush Tewari, Stefanie Wuhrer, Michael Zollhoefer, Thabo Beeler, Florian Bernard, Timo Bolkart, Adam Kortylewski, Sami Romdhani, Christian Theobalt, Volker Blanz, Thomas Vetter


  Access Paper or Ask Questions

Compositional Convolutional Networks For Robust Object Classification under Occlusion


May 29, 2019
Adam Kortylewski, Qing Liu, Huiyu Wang, Zhishuai Zhang, Alan Yuille


  Access Paper or Ask Questions

SkelNetOn 2019 Dataset and Challenge on Deep Learning for Geometric Shape Understanding


Mar 21, 2019
Ilke Demir, Camilla Hahn, Kathryn Leonard, Geraldine Morin, Dana Rahbani, Athina Panotopoulou, Amelie Fondevilla, Elena Balashova, Bastien Durix, Adam Kortylewski

* Dataset paper for SkelNetOn Challenge, in association with Deep Learning for Geometric Shape Understanding Workshop at CVPR 2019 

  Access Paper or Ask Questions

Informed MCMC with Bayesian Neural Networks for Facial Image Analysis


Nov 29, 2018
Adam Kortylewski, Mario Wieser, Andreas Morel-Forster, Aleksander Wieczorek, Sonali Parbhoo, Volker Roth, Thomas Vetter

* Accepted to the Bayesian Deep Learning Workshop at NeurIPS 2018 

  Access Paper or Ask Questions

Priming Deep Neural Networks with Synthetic Faces for Enhanced Performance


Nov 19, 2018
Adam Kortylewski, Andreas Schneider, Thomas Gerig, Clemens Blumer, Bernhard Egger, Corius Reyneke, Andreas Morel-Forster, Thomas Vetter

* Preprint. arXiv admin note: text overlap with arXiv:1802.05891 

  Access Paper or Ask Questions

Greedy Structure Learning of Hierarchical Compositional Models


May 29, 2018
Adam Kortylewski, Clemens Blumer, Andreas Morel-Forster, Thomas Vetter

* Preprint 

  Access Paper or Ask Questions