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 Alexander Binder

Alexander Binder
Alert button

Optimizing Explanations by Network Canonization and Hyperparameter Search


Nov 30, 2022
Frederik Pahde, Galip Ãœmit Yolcu, Alexander Binder, Wojciech Samek, Sebastian Lapuschkin

Add code
Alert button

Figure 1 for Optimizing Explanations by Network Canonization and Hyperparameter Search
Figure 2 for Optimizing Explanations by Network Canonization and Hyperparameter Search
Figure 3 for Optimizing Explanations by Network Canonization and Hyperparameter Search
Figure 4 for Optimizing Explanations by Network Canonization and Hyperparameter Search

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations


Nov 22, 2022
Alexander Binder, Leander Weber, Sebastian Lapuschkin, Grégoire Montavon, Klaus-Robert Müller, Wojciech Samek

Add code
Alert button

Figure 1 for Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations
Figure 2 for Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations
Figure 3 for Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations
Figure 4 for Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations
* 23 pages 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Discovering Transferable Forensic Features for CNN-generated Images Detection


Aug 24, 2022
Keshigeyan Chandrasegaran, Ngoc-Trung Tran, Alexander Binder, Ngai-Man Cheung

Add code
Alert button

Figure 1 for Discovering Transferable Forensic Features for CNN-generated Images Detection
Figure 2 for Discovering Transferable Forensic Features for CNN-generated Images Detection
Figure 3 for Discovering Transferable Forensic Features for CNN-generated Images Detection
Figure 4 for Discovering Transferable Forensic Features for CNN-generated Images Detection
* ECCV 2022 Oral; 35 pages 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement


Mar 15, 2022
Leander Weber, Sebastian Lapuschkin, Alexander Binder, Wojciech Samek

Add code
Alert button

Figure 1 for Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement
Figure 2 for Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement
Figure 3 for Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement
Figure 4 for Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples


Oct 24, 2021
Yi Xiang Marcus Tan, Penny Chong, Jiamei Sun, Ngai-man Cheung, Yuval Elovici, Alexander Binder

Add code
Alert button

Figure 1 for Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples
Figure 2 for Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples
Figure 3 for Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples
Figure 4 for Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples
* arXiv admin note: text overlap with arXiv:2012.06330 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy


Jun 25, 2021
Vignesh Srinivasan, Nils Strodthoff, Jackie Ma, Alexander Binder, Klaus-Robert Müller, Wojciech Samek

Add code
Alert button

Figure 1 for On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy
Figure 2 for On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy
Figure 3 for On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy
Figure 4 for On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Detection of Adversarial Supports in Few-shot Classifiers Using Feature Preserving Autoencoders and Self-Similarity


Dec 09, 2020
Yi Xiang Marcus Tan, Penny Chong, Jiamei Sun, Yuval Elovici, Alexander Binder

Add code
Alert button

Figure 1 for Detection of Adversarial Supports in Few-shot Classifiers Using Feature Preserving Autoencoders and Self-Similarity
Figure 2 for Detection of Adversarial Supports in Few-shot Classifiers Using Feature Preserving Autoencoders and Self-Similarity
Figure 3 for Detection of Adversarial Supports in Few-shot Classifiers Using Feature Preserving Autoencoders and Self-Similarity
Figure 4 for Detection of Adversarial Supports in Few-shot Classifiers Using Feature Preserving Autoencoders and Self-Similarity

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Deja vu from the SVM Era: Example-based Explanations with Outlier Detection


Nov 11, 2020
Penny Chong, Yuval Elovici, Alexander Binder

Add code
Alert button

Figure 1 for Deja vu from the SVM Era: Example-based Explanations with Outlier Detection
Figure 2 for Deja vu from the SVM Era: Example-based Explanations with Outlier Detection
Figure 3 for Deja vu from the SVM Era: Example-based Explanations with Outlier Detection
Figure 4 for Deja vu from the SVM Era: Example-based Explanations with Outlier Detection

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Lymphocyte counting -- Error Analysis of Regression versus Bounding Box Detection Approaches


Jul 21, 2020
Lin Geng Foo, Alexander Binder

Add code
Alert button

Figure 1 for Lymphocyte counting -- Error Analysis of Regression versus Bounding Box Detection Approaches
Figure 2 for Lymphocyte counting -- Error Analysis of Regression versus Bounding Box Detection Approaches
Figure 3 for Lymphocyte counting -- Error Analysis of Regression versus Bounding Box Detection Approaches
Figure 4 for Lymphocyte counting -- Error Analysis of Regression versus Bounding Box Detection Approaches
* Submitted to ICPR 2020 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Explanation-Guided Training for Cross-Domain Few-Shot Classification


Jul 17, 2020
Jiamei Sun, Sebastian Lapuschkin, Wojciech Samek, Yunqing Zhao, Ngai-Man Cheung, Alexander Binder

Add code
Alert button

Figure 1 for Explanation-Guided Training for Cross-Domain Few-Shot Classification
Figure 2 for Explanation-Guided Training for Cross-Domain Few-Shot Classification
Figure 3 for Explanation-Guided Training for Cross-Domain Few-Shot Classification
Figure 4 for Explanation-Guided Training for Cross-Domain Few-Shot Classification

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>