Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactuals
Saloni Dash, Vineeth Balasubramanian, Amit Sharma
Winter Conference on Applications of Computer Vision (WACV) | January 2022
Publications
Publications par année
-
-
Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End
Ramaravind Kommiya Mothilal, Divyat Mahajan, Chenhao Tan, Amit Sharma
AAAI/ACM Conference on AI, Ethics, and Society (AIES) | April 2021
The Importance of Modeling Data Missingness in Algorithmic Fairness: A Causal Perspective
Naman Goel, Alfonso Amayeulas, Amit Deshpande, Amit Sharma
AAAI Conference on Artificial Intelligence (AAAI) | February 2021
-
Inframarginality Audit of Group-Fairness
Amit Sharma, Arpita Biswas, Siddharth Barman
June 2020
Explaining Machine Learning Classifiers through Diverse Counterfactual Examples
Ramaravind K. Mothilal, Amit Sharma, Chenhao Tan
ACM Conference on Fairness, Accountability, and Transparency | January 2020
Filtre par zone de recherche
-
Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactuals
Saloni Dash, Vineeth Balasubramanian, Amit Sharma
Winter Conference on Applications of Computer Vision (WACV) | January 2022
Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End
Ramaravind Kommiya Mothilal, Divyat Mahajan, Chenhao Tan, Amit Sharma
AAAI/ACM Conference on AI, Ethics, and Society (AIES) | April 2021
The Importance of Modeling Data Missingness in Algorithmic Fairness: A Causal Perspective
Naman Goel, Alfonso Amayeulas, Amit Deshpande, Amit Sharma
AAAI Conference on Artificial Intelligence (AAAI) | February 2021
Inframarginality Audit of Group-Fairness
Amit Sharma, Arpita Biswas, Siddharth Barman
June 2020
Explaining Machine Learning Classifiers through Diverse Counterfactual Examples
Ramaravind K. Mothilal, Amit Sharma, Chenhao Tan
ACM Conference on Fairness, Accountability, and Transparency | January 2020
Publication Type
-
Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactuals
Saloni Dash, Vineeth Balasubramanian, Amit Sharma
Winter Conference on Applications of Computer Vision (WACV) | January 2022
Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End
Ramaravind Kommiya Mothilal, Divyat Mahajan, Chenhao Tan, Amit Sharma
AAAI/ACM Conference on AI, Ethics, and Society (AIES) | April 2021
The Importance of Modeling Data Missingness in Algorithmic Fairness: A Causal Perspective
Naman Goel, Alfonso Amayeulas, Amit Deshpande, Amit Sharma
AAAI Conference on Artificial Intelligence (AAAI) | February 2021
Explaining Machine Learning Classifiers through Diverse Counterfactual Examples
Ramaravind K. Mothilal, Amit Sharma, Chenhao Tan
ACM Conference on Fairness, Accountability, and Transparency | January 2020
-
Inframarginality Audit of Group-Fairness
Amit Sharma, Arpita Biswas, Siddharth Barman
June 2020