Alert button
Picture for Karsten Roth

Karsten Roth

Alert button

Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models

Add code
Bookmark button
Alert button
May 02, 2024
Nishad Singhi, Jae Myung Kim, Karsten Roth, Zeynep Akata

Viaarxiv icon

kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies

Add code
Bookmark button
Alert button
Apr 15, 2024
Zhongrui Gui, Shuyang Sun, Runjia Li, Jianhao Yuan, Zhaochong An, Karsten Roth, Ameya Prabhu, Philip Torr

Viaarxiv icon

Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model

Add code
Bookmark button
Alert button
Oct 26, 2023
Karsten Roth, Lukas Thede, Almut Sophia Koepke, Oriol Vinyals, Olivier Hénaff, Zeynep Akata

Viaarxiv icon

Vision-by-Language for Training-Free Compositional Image Retrieval

Add code
Bookmark button
Alert button
Oct 13, 2023
Shyamgopal Karthik, Karsten Roth, Massimiliano Mancini, Zeynep Akata

Figure 1 for Vision-by-Language for Training-Free Compositional Image Retrieval
Figure 2 for Vision-by-Language for Training-Free Compositional Image Retrieval
Figure 3 for Vision-by-Language for Training-Free Compositional Image Retrieval
Figure 4 for Vision-by-Language for Training-Free Compositional Image Retrieval
Viaarxiv icon

Waffling around for Performance: Visual Classification with Random Words and Broad Concepts

Add code
Bookmark button
Alert button
Jun 12, 2023
Karsten Roth, Jae Myung Kim, A. Sophia Koepke, Oriol Vinyals, Cordelia Schmid, Zeynep Akata

Figure 1 for Waffling around for Performance: Visual Classification with Random Words and Broad Concepts
Figure 2 for Waffling around for Performance: Visual Classification with Random Words and Broad Concepts
Figure 3 for Waffling around for Performance: Visual Classification with Random Words and Broad Concepts
Figure 4 for Waffling around for Performance: Visual Classification with Random Words and Broad Concepts
Viaarxiv icon

If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection

Add code
Bookmark button
Alert button
May 22, 2023
Shyamgopal Karthik, Karsten Roth, Massimiliano Mancini, Zeynep Akata

Figure 1 for If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection
Figure 2 for If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection
Figure 3 for If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection
Figure 4 for If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection
Viaarxiv icon

Momentum-based Weight Interpolation of Strong Zero-Shot Models for Continual Learning

Add code
Bookmark button
Alert button
Nov 06, 2022
Zafir Stojanovski, Karsten Roth, Zeynep Akata

Figure 1 for Momentum-based Weight Interpolation of Strong Zero-Shot Models for Continual Learning
Figure 2 for Momentum-based Weight Interpolation of Strong Zero-Shot Models for Continual Learning
Figure 3 for Momentum-based Weight Interpolation of Strong Zero-Shot Models for Continual Learning
Figure 4 for Momentum-based Weight Interpolation of Strong Zero-Shot Models for Continual Learning
Viaarxiv icon

Disentanglement of Correlated Factors via Hausdorff Factorized Support

Add code
Bookmark button
Alert button
Oct 13, 2022
Karsten Roth, Mark Ibrahim, Zeynep Akata, Pascal Vincent, Diane Bouchacourt

Figure 1 for Disentanglement of Correlated Factors via Hausdorff Factorized Support
Figure 2 for Disentanglement of Correlated Factors via Hausdorff Factorized Support
Figure 3 for Disentanglement of Correlated Factors via Hausdorff Factorized Support
Figure 4 for Disentanglement of Correlated Factors via Hausdorff Factorized Support
Viaarxiv icon

A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning

Add code
Bookmark button
Alert button
Jul 08, 2022
Michael Kirchhof, Karsten Roth, Zeynep Akata, Enkelejda Kasneci

Figure 1 for A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning
Figure 2 for A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning
Figure 3 for A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning
Figure 4 for A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning
Viaarxiv icon

Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning

Add code
Bookmark button
Alert button
Mar 23, 2022
Natalie Dullerud, Karsten Roth, Kimia Hamidieh, Nicolas Papernot, Marzyeh Ghassemi

Figure 1 for Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning
Figure 2 for Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning
Figure 3 for Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning
Figure 4 for Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning
Viaarxiv icon