Picture for Ali Borji

Ali Borji

SalFoM: Dynamic Saliency Prediction with Video Foundation Models

Apr 03, 2024
Viaarxiv icon

Key-Value Transformer

Add code
May 28, 2023
Figure 1 for Key-Value Transformer
Figure 2 for Key-Value Transformer
Figure 3 for Key-Value Transformer
Figure 4 for Key-Value Transformer
Viaarxiv icon

Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes

Add code
Mar 29, 2023
Figure 1 for Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes
Figure 2 for Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes
Figure 3 for Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes
Figure 4 for Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes
Viaarxiv icon

A Categorical Archive of ChatGPT Failures

Add code
Feb 23, 2023
Figure 1 for A Categorical Archive of ChatGPT Failures
Figure 2 for A Categorical Archive of ChatGPT Failures
Figure 3 for A Categorical Archive of ChatGPT Failures
Figure 4 for A Categorical Archive of ChatGPT Failures
Viaarxiv icon

Diverse, Difficult, and Odd Instances (D2O): A New Test Set for Object Classification

Add code
Jan 29, 2023
Figure 1 for Diverse, Difficult, and Odd Instances (D2O): A New Test Set for Object Classification
Figure 2 for Diverse, Difficult, and Odd Instances (D2O): A New Test Set for Object Classification
Figure 3 for Diverse, Difficult, and Odd Instances (D2O): A New Test Set for Object Classification
Figure 4 for Diverse, Difficult, and Odd Instances (D2O): A New Test Set for Object Classification
Viaarxiv icon

BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models

Add code
Jan 28, 2023
Figure 1 for BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models
Figure 2 for BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models
Figure 3 for BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models
Figure 4 for BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models
Viaarxiv icon

Logits are predictive of network type

Add code
Nov 04, 2022
Figure 1 for Logits are predictive of network type
Figure 2 for Logits are predictive of network type
Figure 3 for Logits are predictive of network type
Figure 4 for Logits are predictive of network type
Viaarxiv icon

Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2

Add code
Oct 02, 2022
Figure 1 for Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2
Figure 2 for Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2
Figure 3 for Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2
Figure 4 for Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2
Viaarxiv icon

How good are deep models in understanding the generated images?

Aug 25, 2022
Figure 1 for How good are deep models in understanding the generated images?
Figure 2 for How good are deep models in understanding the generated images?
Figure 3 for How good are deep models in understanding the generated images?
Figure 4 for How good are deep models in understanding the generated images?
Viaarxiv icon

Is current research on adversarial robustness addressing the right problem?

Aug 04, 2022
Figure 1 for Is current research on adversarial robustness addressing the right problem?
Figure 2 for Is current research on adversarial robustness addressing the right problem?
Figure 3 for Is current research on adversarial robustness addressing the right problem?
Figure 4 for Is current research on adversarial robustness addressing the right problem?
Viaarxiv icon