Sepehr Dehdashtian

According to our database, Sepehr Dehdashtian authored at least 8 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors.

Sepehr Dehdashtian, Mashrur M. Morshed, Jacob H. Seidman, Gaurav Bharaj, Vishnu Naresh Boddeti

CoRR, September, 2025

OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes.

Sepehr Dehdashtian, Gautam Sreekumar, Vishnu Boddeti

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Fairness and Bias Mitigation in Computer Vision: A Survey.

Sepehr Dehdashtian, Ruozhen He, Yi Li, Guha Balakrishnan, Nuno Vasconcelos, Vicente Ordonez, Vishnu Naresh Boddeti

CoRR, 2024

FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs.

Sepehr Dehdashtian, Lan Wang, Vishnu Boddeti

Proceedings of the Twelfth International Conference on Learning Representations, 2024

The Dark Side of Dataset Scaling: Evaluating Racial Classification in Multimodal Models.

Abeba Birhane, Sepehr Dehdashtian, Vinay Uday Prabhu, Vishnu Boddeti

Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency, 2024

Utility-Fairness Trade-Offs and how to Find Them.

Sepehr Dehdashtian, Bashir Sadeghi, Vishnu Naresh Boddeti

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2022

On Characterizing the Trade-off in Invariant Representation Learning.

Bashir Sadeghi, Sepehr Dehdashtian, Vishnu Boddeti

Trans. Mach. Learn. Res., 2022

2021

Deep-Learning-Based Blind Recognition of Channel Code Parameters Over Candidate Sets Under AWGN and Multi-Path Fading Conditions.

Sepehr Dehdashtian, Matin Hashemi, Saber Salehkaleybar

IEEE Wirel. Commun. Lett., 2021