Sahar Rahimi Malakshan — accepted AI-conference papers

2024

ARoFace: Alignment Robustness to Improve Low-quality Face Recognition

Mohammad Saeed Ebrahimi Saadabadi*, Sahar Rahimi Malakshan, Ali Dabouei, Nasser Nasrabadi

ECCV 2024poster

"Aiming to enhance Face Recognition (FR) on Low-Quality (LQ) inputs, recent studies suggest incorporating synthetic LQ samples into training. Although promising, the quality factors that are considered in these works are general rather than FR-specific, , atmospheric turbulence, resolution, . Motiva…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2024

Hyperspherical Classification with Dynamic Label-to-Prototype Assignment

Mohammad Saeed Ebrahimi Saadabadi, Ali Dabouei, Sahar Rahimi Malakshan, Nasser M. Nasrabadi

CVPR 2024poster

Aiming to enhance the utilization of metric space by the parametric softmax classifier recent studies suggest replacing it with a non-parametric alternative. Although a non-parametric classifier may provide better metric space utilization it introduces the challenge of capturing inter-class relation…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗