Alert button
Picture for Peter Gehler

Peter Gehler

Alert button

TeST: Test-time Self-Training under Distribution Shift

Sep 23, 2022
Samarth Sinha, Peter Gehler, Francesco Locatello, Bernt Schiele

Figure 1 for TeST: Test-time Self-Training under Distribution Shift
Figure 2 for TeST: Test-time Self-Training under Distribution Shift
Figure 3 for TeST: Test-time Self-Training under Distribution Shift
Figure 4 for TeST: Test-time Self-Training under Distribution Shift
Viaarxiv icon

Unsupervised Object Learning via Common Fate

Oct 13, 2021
Matthias Tangemann, Steffen Schneider, Julius von Kügelgen, Francesco Locatello, Peter Gehler, Thomas Brox, Matthias Kümmerer, Matthias Bethge, Bernhard Schölkopf

Figure 1 for Unsupervised Object Learning via Common Fate
Figure 2 for Unsupervised Object Learning via Common Fate
Figure 3 for Unsupervised Object Learning via Common Fate
Figure 4 for Unsupervised Object Learning via Common Fate
Viaarxiv icon

Dynamic Inference with Neural Interpreters

Oct 12, 2021
Nasim Rahaman, Muhammad Waleed Gondal, Shruti Joshi, Peter Gehler, Yoshua Bengio, Francesco Locatello, Bernhard Schölkopf

Figure 1 for Dynamic Inference with Neural Interpreters
Figure 2 for Dynamic Inference with Neural Interpreters
Figure 3 for Dynamic Inference with Neural Interpreters
Figure 4 for Dynamic Inference with Neural Interpreters
Viaarxiv icon

You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction

Oct 11, 2021
Osama Makansi, Julius von Kügelgen, Francesco Locatello, Peter Gehler, Dominik Janzing, Thomas Brox, Bernhard Schölkopf

Figure 1 for You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction
Figure 2 for You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction
Figure 3 for You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction
Figure 4 for You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction
Viaarxiv icon

CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations

Sep 30, 2021
Mohammadreza Zolfaghari, Yi Zhu, Peter Gehler, Thomas Brox

Figure 1 for CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations
Figure 2 for CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations
Figure 3 for CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations
Figure 4 for CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations
Viaarxiv icon

Visual Representation Learning Does Not Generalize Strongly Within the Same Domain

Jul 23, 2021
Lukas Schott, Julius von Kügelgen, Frederik Träuble, Peter Gehler, Chris Russell, Matthias Bethge, Bernhard Schölkopf, Francesco Locatello, Wieland Brendel

Figure 1 for Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
Figure 2 for Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
Figure 3 for Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
Figure 4 for Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
Viaarxiv icon

Representation Learning for Out-Of-Distribution Generalization in Reinforcement Learning

Jul 12, 2021
Andrea Dittadi, Frederik Träuble, Manuel Wüthrich, Felix Widmaier, Peter Gehler, Ole Winther, Francesco Locatello, Olivier Bachem, Bernhard Schölkopf, Stefan Bauer

Figure 1 for Representation Learning for Out-Of-Distribution Generalization in Reinforcement Learning
Figure 2 for Representation Learning for Out-Of-Distribution Generalization in Reinforcement Learning
Figure 3 for Representation Learning for Out-Of-Distribution Generalization in Reinforcement Learning
Figure 4 for Representation Learning for Out-Of-Distribution Generalization in Reinforcement Learning
Viaarxiv icon

Backward-Compatible Prediction Updates: A Probabilistic Approach

Jul 02, 2021
Frederik Träuble, Julius von Kügelgen, Matthäus Kleindessner, Francesco Locatello, Bernhard Schölkopf, Peter Gehler

Figure 1 for Backward-Compatible Prediction Updates: A Probabilistic Approach
Figure 2 for Backward-Compatible Prediction Updates: A Probabilistic Approach
Figure 3 for Backward-Compatible Prediction Updates: A Probabilistic Approach
Figure 4 for Backward-Compatible Prediction Updates: A Probabilistic Approach
Viaarxiv icon

Towards Total Recall in Industrial Anomaly Detection

Jun 15, 2021
Karsten Roth, Latha Pemula, Joaquin Zepeda, Bernhard Schölkopf, Thomas Brox, Peter Gehler

Figure 1 for Towards Total Recall in Industrial Anomaly Detection
Figure 2 for Towards Total Recall in Industrial Anomaly Detection
Figure 3 for Towards Total Recall in Industrial Anomaly Detection
Figure 4 for Towards Total Recall in Industrial Anomaly Detection
Viaarxiv icon