关注
Mazda Moayeri
Mazda Moayeri
在 umd.edu 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
A comprehensive study of image classification model sensitivity to foregrounds, backgrounds, and visual attributes
M Moayeri, P Pope, Y Balaji, S Feizi
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
482022
Text-to-concept (and back) via cross-model alignment
M Moayeri, K Rezaei, M Sanjabi, S Feizi
International Conference on Machine Learning, 25037-25060, 2023
272023
Sample efficient detection and classification of adversarial attacks via self-supervised embeddings
M Moayeri, S Feizi
Proceedings of the IEEE/CVF international conference on computer vision …, 2021
272021
Explicit tradeoffs between adversarial and natural distributional robustness
M Moayeri, K Banihashem, S Feizi
Advances in Neural Information Processing Systems 35, 38761-38774, 2022
212022
Hard imagenet: Segmentations for objects with strong spurious cues
M Moayeri, S Singla, S Feizi
Advances in Neural Information Processing Systems 35, 10068-10077, 2022
202022
A holistic approach to unifying automatic concept extraction and concept importance estimation
T Fel, V Boutin, L Béthune, R Cadène, M Moayeri, L Andéol, M Chalvidal, ...
Advances in Neural Information Processing Systems 36, 2024
162024
Core risk minimization using salient imagenet
S Singla, M Moayeri, S Feizi
arXiv preprint arXiv:2203.15566, 2022
82022
An introduction to vision-language modeling
F Bordes, RY Pang, A Ajay, AC Li, A Bardes, S Petryk, O Mañas, Z Lin, ...
arXiv preprint arXiv:2405.17247, 2024
72024
Neural symbolic music genre transfer insights
G Brunner, M Moayeri, O Richter, R Wattenhofer, C Zhang
Machine Learning and Knowledge Discovery in Databases: International …, 2020
62020
Data-centric debugging: mitigating model failures via targeted data collection
S Singla, AM Chegini, M Moayeri, S Feiz
arXiv preprint arXiv:2211.09859, 2022
52022
Spuriosity rankings: sorting data to measure and mitigate biases
M Moayeri, W Wang, S Singla, S Feizi
Advances in Neural Information Processing Systems 36, 41572-41600, 2023
32023
Text2concept: Concept activation vectors directly from text
M Moayeri, K Rezaei, M Sanjabi, S Feizi
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
32023
Spuriosity rankings: Sorting data for spurious correlation robustness
M Moayeri, W Wang, S Singla, S Feizi
arXiv preprint arXiv:2212.02648, 2022
32022
PRIME: Prioritizing Interpretability in Failure Mode Extraction
K Rezaei, M Saberi, M Moayeri, S Feizi
arXiv preprint arXiv:2310.00164, 2023
22023
WorldBench: Quantifying Geographic Disparities in LLM Factual Recall
M Moayeri, E Tabassi, S Feizi
The 2024 ACM Conference on Fairness, Accountability, and Transparency, 1211-1228, 2024
12024
Embracing Diversity: Interpretable Zero-shot classification beyond one vector per class
M Moayeri, M Rabbat, M Ibrahim, D Bouchacourt
The 2024 ACM Conference on Fairness, Accountability, and Transparency, 2302-2321, 2024
12024
Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models
M Moayeri, S Basu, S Balasubramanian, P Kattakinda, A Chengini, ...
arXiv preprint arXiv:2404.08030, 2024
12024
Understanding and Mitigating Compositional Issues in Text-to-Image Generative Models
A Zarei, K Rezaei, S Basu, M Saberi, M Moayeri, P Kattakinda, S Feizi
arXiv preprint arXiv:2406.07844, 2024
2024
Data-Centric Debugging: mitigating model failures via targeted image retrieval
S Singla, AM Chegini, M Moayeri, S Feizi
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2024
2024
Embracing Diversity: Zero-shot Classification Beyond a Single Vector per Class
M Moayeri, M Rabbat, M Ibrahim, D Bouchacourt
系统目前无法执行此操作,请稍后再试。
文章 1–20