Crowd counting with decomposed uncertainty
- Min Hwan Oh
- Peder Olsen
- et al.
- 2020
- AAAI 2020
Conference paper
Publications
960 results for Trustworthy AI
Towards query-efficient black-box adversary with zeroth-order natural gradient descent
- Pu Zhao
- Pin-Yu Chen
- et al.
- 2020
- AAAI 2020
Conference paperData augmentation for discrimination prevention and bias disambiguation
- Shubham Sharma
- Yunfeng Zhang
- et al.
- 2020
- AIES 2020
Conference paperCAG: A real-time low-cost enhanced-robustness high-transferability content-aware adversarial attack generator
- Huy Phan
- Yi Xie
- et al.
- 2020
- AAAI 2020
Conference paperFair enough: Improving fairness in budget-constrained decision making using confidence thresholds
- Michiel A. Bakker
- Humberto Riverón Valdés
- et al.
- 2020
- SafeAI 2020
Conference paperSeq2sick: Evaluating the robustness of sequence-to-sequence models with adversarial examples
- Minhao Cheng
- Jinfeng Yi
- et al.
- 2020
- AAAI 2020
Conference paperBuilding calibrated deep models via uncertainty matching with auxiliary interval predictors
- Jayaraman J. Thiagarajan
- Bindya Venkatesh
- et al.
- 2020
- AAAI 2020
Conference paperTowards certificated model robustness against weight perturbations
- Tsui Wei Weng
- Pu Zhao
- et al.
- 2020
- AAAI 2020
Conference paperQuality Management of Machine Learning Systems
- Peter Santhanam
- 2020
- AAAI 2020
Workshop paperEffect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making
- Yunfeng Zhang
- Q. Vera Liao
- et al.
- 2020
- FAccT 2020
Conference paper