Alert button
Picture for Thomas Breuel

Thomas Breuel

Alert button

Investigating the Nature of 3D Generalization in Deep Neural Networks

Apr 19, 2023
Shoaib Ahmed Siddiqui, David Krueger, Thomas Breuel

Figure 1 for Investigating the Nature of 3D Generalization in Deep Neural Networks
Figure 2 for Investigating the Nature of 3D Generalization in Deep Neural Networks
Figure 3 for Investigating the Nature of 3D Generalization in Deep Neural Networks
Figure 4 for Investigating the Nature of 3D Generalization in Deep Neural Networks
Viaarxiv icon

GroupViT: Semantic Segmentation Emerges from Text Supervision

Feb 22, 2022
Jiarui Xu, Shalini De Mello, Sifei Liu, Wonmin Byeon, Thomas Breuel, Jan Kautz, Xiaolong Wang

Figure 1 for GroupViT: Semantic Segmentation Emerges from Text Supervision
Figure 2 for GroupViT: Semantic Segmentation Emerges from Text Supervision
Figure 3 for GroupViT: Semantic Segmentation Emerges from Text Supervision
Figure 4 for GroupViT: Semantic Segmentation Emerges from Text Supervision
Viaarxiv icon

Identifying Layers Susceptible to Adversarial Attacks

Jul 10, 2021
Shoaib Ahmed Siddiqui, Thomas Breuel

Figure 1 for Identifying Layers Susceptible to Adversarial Attacks
Figure 2 for Identifying Layers Susceptible to Adversarial Attacks
Figure 3 for Identifying Layers Susceptible to Adversarial Attacks
Figure 4 for Identifying Layers Susceptible to Adversarial Attacks
Viaarxiv icon

Automatic Curation of Large-Scale Datasets for Audio-Visual Representation Learning

Jan 26, 2021
Sangho Lee, Jiwan Chung, Youngjae Yu, Gunhee Kim, Thomas Breuel, Gal Chechik, Yale Song

Figure 1 for Automatic Curation of Large-Scale Datasets for Audio-Visual Representation Learning
Figure 2 for Automatic Curation of Large-Scale Datasets for Audio-Visual Representation Learning
Figure 3 for Automatic Curation of Large-Scale Datasets for Audio-Visual Representation Learning
Figure 4 for Automatic Curation of Large-Scale Datasets for Audio-Visual Representation Learning
Viaarxiv icon

Parameter Efficient Multimodal Transformers for Video Representation Learning

Dec 08, 2020
Sangho Lee, Youngjae Yu, Gunhee Kim, Thomas Breuel, Jan Kautz, Yale Song

Figure 1 for Parameter Efficient Multimodal Transformers for Video Representation Learning
Figure 2 for Parameter Efficient Multimodal Transformers for Video Representation Learning
Figure 3 for Parameter Efficient Multimodal Transformers for Video Representation Learning
Figure 4 for Parameter Efficient Multimodal Transformers for Video Representation Learning
Viaarxiv icon

Displacement-Invariant Cost Computation for Efficient Stereo Matching

Dec 01, 2020
Yiran Zhong, Charles Loop, Wonmin Byeon, Stan Birchfield, Yuchao Dai, Kaihao Zhang, Alexey Kamenev, Thomas Breuel, Hongdong Li, Jan Kautz

Figure 1 for Displacement-Invariant Cost Computation for Efficient Stereo Matching
Figure 2 for Displacement-Invariant Cost Computation for Efficient Stereo Matching
Figure 3 for Displacement-Invariant Cost Computation for Efficient Stereo Matching
Figure 4 for Displacement-Invariant Cost Computation for Efficient Stereo Matching
Viaarxiv icon

Discovering Nonlinear Relations with Minimum Predictive Information Regularization

Jan 07, 2020
Tailin Wu, Thomas Breuel, Michael Skuhersky, Jan Kautz

Figure 1 for Discovering Nonlinear Relations with Minimum Predictive Information Regularization
Figure 2 for Discovering Nonlinear Relations with Minimum Predictive Information Regularization
Figure 3 for Discovering Nonlinear Relations with Minimum Predictive Information Regularization
Viaarxiv icon

Unsupervised Image-to-Image Translation Networks

Jul 23, 2018
Ming-Yu Liu, Thomas Breuel, Jan Kautz

Figure 1 for Unsupervised Image-to-Image Translation Networks
Figure 2 for Unsupervised Image-to-Image Translation Networks
Figure 3 for Unsupervised Image-to-Image Translation Networks
Figure 4 for Unsupervised Image-to-Image Translation Networks
Viaarxiv icon

IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification

Apr 26, 2018
Sam Leroux, Pavlo Molchanov, Pieter Simoens, Bart Dhoedt, Thomas Breuel, Jan Kautz

Figure 1 for IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification
Figure 2 for IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification
Figure 3 for IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification
Viaarxiv icon

Hand Pose Estimation via Latent 2.5D Heatmap Regression

Apr 25, 2018
Umar Iqbal, Pavlo Molchanov, Thomas Breuel, Juergen Gall, Jan Kautz

Figure 1 for Hand Pose Estimation via Latent 2.5D Heatmap Regression
Figure 2 for Hand Pose Estimation via Latent 2.5D Heatmap Regression
Figure 3 for Hand Pose Estimation via Latent 2.5D Heatmap Regression
Figure 4 for Hand Pose Estimation via Latent 2.5D Heatmap Regression
Viaarxiv icon