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 Sanja Fidler

Sanja Fidler

NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation


Jul 04, 2021
Xiaohui Zeng, Raquel Urtasun, Richard Zemel, Sanja Fidler, Renjie Liao

Figure 1 for NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
Figure 2 for NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
Figure 3 for NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
Figure 4 for NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
* UAI2021, code at https://github.com/ZENGXH/NPDRAW 
  Access Paper or Ask Questions

NP-DRAW: A Non-Parametric Structured Latent Variable Modelfor Image Generation


Jun 25, 2021
Xiaohui Zeng, Raquel Urtasun, Richard Zemel, Sanja Fidler, Renjie Liao

Figure 1 for NP-DRAW: A Non-Parametric Structured Latent Variable Modelfor Image Generation
Figure 2 for NP-DRAW: A Non-Parametric Structured Latent Variable Modelfor Image Generation
Figure 3 for NP-DRAW: A Non-Parametric Structured Latent Variable Modelfor Image Generation
Figure 4 for NP-DRAW: A Non-Parametric Structured Latent Variable Modelfor Image Generation
* UAI2021, code at https://github.com/ZENGXH/NPDRAW 
  Access Paper or Ask Questions

f-Domain-Adversarial Learning: Theory and Algorithms


Jun 21, 2021
David Acuna, Guojun Zhang, Marc T. Law, Sanja Fidler

Figure 1 for f-Domain-Adversarial Learning: Theory and Algorithms
Figure 2 for f-Domain-Adversarial Learning: Theory and Algorithms
Figure 3 for f-Domain-Adversarial Learning: Theory and Algorithms
Figure 4 for f-Domain-Adversarial Learning: Theory and Algorithms
* ICML 2021 
  Access Paper or Ask Questions

Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approach


Jun 12, 2021
Rafid Mahmood, Sanja Fidler, Marc T. Law

Figure 1 for Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approach
Figure 2 for Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approach
Figure 3 for Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approach
Figure 4 for Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approach

  Access Paper or Ask Questions

DriveGAN: Towards a Controllable High-Quality Neural Simulation


Apr 30, 2021
Seung Wook Kim, Jonah Philion, Antonio Torralba, Sanja Fidler

Figure 1 for DriveGAN: Towards a Controllable High-Quality Neural Simulation
Figure 2 for DriveGAN: Towards a Controllable High-Quality Neural Simulation
Figure 3 for DriveGAN: Towards a Controllable High-Quality Neural Simulation
Figure 4 for DriveGAN: Towards a Controllable High-Quality Neural Simulation
* CVPR 2021 Oral 
  Access Paper or Ask Questions

Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets


Apr 26, 2021
Yuan-Hong Liao, Amlan Kar, Sanja Fidler

Figure 1 for Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets
Figure 2 for Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets
Figure 3 for Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets
Figure 4 for Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets
* CVPR 2021 Oral 
  Access Paper or Ask Questions

DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort


Apr 20, 2021
Yuxuan Zhang, Huan Ling, Jun Gao, Kangxue Yin, Jean-Francois Lafleche, Adela Barriuso, Antonio Torralba, Sanja Fidler

Figure 1 for DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
Figure 2 for DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
Figure 3 for DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
Figure 4 for DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
* Accepted to CVPR 2021 as an Oral paper. Webpage: https://nv-tlabs.github.io/datasetGAN/ 
  Access Paper or Ask Questions

Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization


Apr 12, 2021
Daiqing Li, Junlin Yang, Karsten Kreis, Antonio Torralba, Sanja Fidler

Figure 1 for Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
Figure 2 for Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
Figure 3 for Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
Figure 4 for Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
* CVPR2021 
  Access Paper or Ask Questions

Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection


Apr 12, 2021
Nadine Chang, Zhiding Yu, Yu-Xiong Wang, Anima Anandkumar, Sanja Fidler, Jose M. Alvarez

Figure 1 for Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection
Figure 2 for Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection
Figure 3 for Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection
Figure 4 for Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection

  Access Paper or Ask Questions

gradSim: Differentiable simulation for system identification and visuomotor control


Apr 06, 2021
Krishna Murthy Jatavallabhula, Miles Macklin, Florian Golemo, Vikram Voleti, Linda Petrini, Martin Weiss, Breandan Considine, Jerome Parent-Levesque, Kevin Xie, Kenny Erleben, Liam Paull, Florian Shkurti, Derek Nowrouzezahrai, Sanja Fidler

Figure 1 for gradSim: Differentiable simulation for system identification and visuomotor control
Figure 2 for gradSim: Differentiable simulation for system identification and visuomotor control
Figure 3 for gradSim: Differentiable simulation for system identification and visuomotor control
Figure 4 for gradSim: Differentiable simulation for system identification and visuomotor control
* ICLR 2021. Project page (and a dynamic web version of the article): https://gradsim.github.io 
  Access Paper or Ask Questions

Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks


Mar 18, 2021
Despoina Paschalidou, Angelos Katharopoulos, Andreas Geiger, Sanja Fidler

Figure 1 for Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks
Figure 2 for Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks
Figure 3 for Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks
Figure 4 for Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks
* To appear in CVPR 2021 
  Access Paper or Ask Questions

Personalized Federated Learning with First Order Model Optimization


Jan 28, 2021
Michael Zhang, Karan Sapra, Sanja Fidler, Serena Yeung, Jose M. Alvarez

Figure 1 for Personalized Federated Learning with First Order Model Optimization
Figure 2 for Personalized Federated Learning with First Order Model Optimization
Figure 3 for Personalized Federated Learning with First Order Model Optimization
Figure 4 for Personalized Federated Learning with First Order Model Optimization
* ICLR 2021 
  Access Paper or Ask Questions

Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes


Jan 26, 2021
Towaki Takikawa, Joey Litalien, Kangxue Yin, Karsten Kreis, Charles Loop, Derek Nowrouzezahrai, Alec Jacobson, Morgan McGuire, Sanja Fidler

Figure 1 for Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes
Figure 2 for Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes
Figure 3 for Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes
Figure 4 for Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes

  Access Paper or Ask Questions

UniCon: Universal Neural Controller For Physics-based Character Motion


Nov 30, 2020
Tingwu Wang, Yunrong Guo, Maria Shugrina, Sanja Fidler

Figure 1 for UniCon: Universal Neural Controller For Physics-based Character Motion
Figure 2 for UniCon: Universal Neural Controller For Physics-based Character Motion
Figure 3 for UniCon: Universal Neural Controller For Physics-based Character Motion
Figure 4 for UniCon: Universal Neural Controller For Physics-based Character Motion
* 15 pages, 15 figures 
  Access Paper or Ask Questions

Emergent Road Rules In Multi-Agent Driving Environments


Nov 21, 2020
Avik Pal, Jonah Philion, Yuan-Hong Liao, Sanja Fidler

Figure 1 for Emergent Road Rules In Multi-Agent Driving Environments
Figure 2 for Emergent Road Rules In Multi-Agent Driving Environments
Figure 3 for Emergent Road Rules In Multi-Agent Driving Environments
Figure 4 for Emergent Road Rules In Multi-Agent Driving Environments
* Project Page: http://fidler-lab.github.io/social-driving 
  Access Paper or Ask Questions

Learning Deformable Tetrahedral Meshes for 3D Reconstruction


Nov 03, 2020
Jun Gao, Wenzheng Chen, Tommy Xiang, Alec Jacobson, Morgan McGuire, Sanja Fidler

Figure 1 for Learning Deformable Tetrahedral Meshes for 3D Reconstruction
Figure 2 for Learning Deformable Tetrahedral Meshes for 3D Reconstruction
Figure 3 for Learning Deformable Tetrahedral Meshes for 3D Reconstruction
Figure 4 for Learning Deformable Tetrahedral Meshes for 3D Reconstruction
* Accepted to NeurIPS 2020 
  Access Paper or Ask Questions

The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes


Oct 24, 2020
Yiluan Guo, Holger Caesar, Oscar Beijbom, Jonah Philion, Sanja Fidler

Figure 1 for The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes
Figure 2 for The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes
Figure 3 for The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes
Figure 4 for The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes
* IROS 2020 Workshop on Benchmarking Progress in Autonomous Driving 
  Access Paper or Ask Questions

Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration


Oct 19, 2020
Xavier Puig, Tianmin Shu, Shuang Li, Zilin Wang, Joshua B. Tenenbaum, Sanja Fidler, Antonio Torralba

Figure 1 for Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
Figure 2 for Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
Figure 3 for Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
Figure 4 for Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration

  Access Paper or Ask Questions

Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering


Oct 18, 2020
Yuxuan Zhang, Wenzheng Chen, Huan Ling, Jun Gao, Yinan Zhang, Antonio Torralba, Sanja Fidler

Figure 1 for Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
Figure 2 for Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
Figure 3 for Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
Figure 4 for Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering

  Access Paper or Ask Questions

Fed-Sim: Federated Simulation for Medical Imaging


Sep 01, 2020
Daiqing Li, Amlan Kar, Nishant Ravikumar, Alejandro F Frangi, Sanja Fidler

Figure 1 for Fed-Sim: Federated Simulation for Medical Imaging
Figure 2 for Fed-Sim: Federated Simulation for Medical Imaging
Figure 3 for Fed-Sim: Federated Simulation for Medical Imaging
Figure 4 for Fed-Sim: Federated Simulation for Medical Imaging
* MICCAI 2020 (Early Accept) 
  Access Paper or Ask Questions

Expressive Telepresence via Modular Codec Avatars


Aug 26, 2020
Hang Chu, Shugao Ma, Fernando De la Torre, Sanja Fidler, Yaser Sheikh

Figure 1 for Expressive Telepresence via Modular Codec Avatars
Figure 2 for Expressive Telepresence via Modular Codec Avatars
Figure 3 for Expressive Telepresence via Modular Codec Avatars
Figure 4 for Expressive Telepresence via Modular Codec Avatars
* ECCV 2020 
  Access Paper or Ask Questions

Interactive Annotation of 3D Object Geometry using 2D Scribbles


Aug 24, 2020
Tianchang Shen, Jun Gao, Amlan Kar, Sanja Fidler

Figure 1 for Interactive Annotation of 3D Object Geometry using 2D Scribbles
Figure 2 for Interactive Annotation of 3D Object Geometry using 2D Scribbles
Figure 3 for Interactive Annotation of 3D Object Geometry using 2D Scribbles
Figure 4 for Interactive Annotation of 3D Object Geometry using 2D Scribbles
* Accepted to ECCV 2020 
  Access Paper or Ask Questions

ScribbleBox: Interactive Annotation Framework for Video Object Segmentation


Aug 22, 2020
Bowen Chen, Huan Ling, Xiaohui Zeng, Gao Jun, Ziyue Xu, Sanja Fidler

Figure 1 for ScribbleBox: Interactive Annotation Framework for Video Object Segmentation
Figure 2 for ScribbleBox: Interactive Annotation Framework for Video Object Segmentation
Figure 3 for ScribbleBox: Interactive Annotation Framework for Video Object Segmentation
Figure 4 for ScribbleBox: Interactive Annotation Framework for Video Object Segmentation

  Access Paper or Ask Questions

Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid


Aug 21, 2020
Jun Gao, Zian Wang, Jinchen Xuan, Sanja Fidler

Figure 1 for Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid
Figure 2 for Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid
Figure 3 for Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid
Figure 4 for Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid
* ECCV 2020 
  Access Paper or Ask Questions

Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation


Aug 20, 2020
Jeevan Devaranjan, Amlan Kar, Sanja Fidler

Figure 1 for Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation
Figure 2 for Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation
Figure 3 for Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation
Figure 4 for Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generation
* ECCV 2020 
  Access Paper or Ask Questions

Learning to Generate Diverse Dance Motions with Transformer


Aug 18, 2020
Jiaman Li, Yihang Yin, Hang Chu, Yi Zhou, Tingwu Wang, Sanja Fidler, Hao Li

Figure 1 for Learning to Generate Diverse Dance Motions with Transformer
Figure 2 for Learning to Generate Diverse Dance Motions with Transformer
Figure 3 for Learning to Generate Diverse Dance Motions with Transformer
Figure 4 for Learning to Generate Diverse Dance Motions with Transformer

  Access Paper or Ask Questions