Erfani, Sarah

11 publications

WACV 2025 Exploiting Inter-Sample Information for Long-Tailed Out-of-Distribution Detection Nimeshika Udayangani, Hadi Mohaghegh Dolatabadi, Sarah Erfani, Christopher Leckie

WACV 2024 Learning Transferable Representations for Image Anomaly Localization Using Dense Pretraining Haitian He, Sarah Erfani, Mingming Gong, Qiuhong Ke

NeurIPS 2022 Double Bubble, Toil and Trouble: Enhancing Certified Robustness Through Transitivity Andrew Cullen, Paul Montague, Shijie Liu, Sarah Erfani, Benjamin I. Rubinstein

ECCV 2022 L∞-Robustness and Beyond: Unleashing Efficient Adversarial Training Hadi M. Dolatabadi, Sarah Erfani, Christopher Leckie

NeurIPS 2021 $\alpha$-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression Jiabo He, Sarah Erfani, Xingjun Ma, James Bailey, Ying Chi, Xian-Sheng Hua

NeurIPS 2021 Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks Hanxun Huang, Yisen Wang, Sarah Erfani, Quanquan Gu, James Bailey, Xingjun Ma

ACML 2021 Generating Deep Networks Explanations with Robust Attribution Alignment Guohang Zeng, Yousef Kowsar, Sarah Erfani, James Bailey

NeurIPS 2020 AdvFlow: Inconspicuous Black-Box Adversarial Attacks Using Normalizing Flows Hadi Mohaghegh Dolatabadi, Sarah Erfani, Christopher Leckie

AISTATS 2020 Invertible Generative Modeling Using Linear Rational Splines Hadi Mohaghegh Dolatabadi, Sarah Erfani, Christopher Leckie

ICML 2020 Normalized Loss Functions for Deep Learning with Noisy Labels Xingjun Ma, Hanxun Huang, Yisen Wang, Simone Romano, Sarah Erfani, James Bailey

ICML 2018 Dimensionality-Driven Learning with Noisy Labels Xingjun Ma, Yisen Wang, Michael E. Houle, Shuo Zhou, Sarah Erfani, Shutao Xia, Sudanthi Wijewickrema, James Bailey