Search Results for author: Abouzar Eslami

Found 10 papers, 5 papers with code

Quantile-based Maximum Likelihood Training for Outlier Detection

1 code implementation20 Aug 2023 Masoud Taghikhah, Nishant Kumar, Siniša Šegvić, Abouzar Eslami, Stefan Gumhold

Previous attempts to address this challenge involved training image classifiers through contrastive learning using actual outlier data or synthesizing outliers for self-supervised learning.

Autonomous Driving Contrastive Learning +3

Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detection

1 code implementation CVPR 2023 Nishant Kumar, Siniša Šegvić, Abouzar Eslami, Stefan Gumhold

However, this strategy does not guarantee that the synthesized outlier features will have a low likelihood according to the other class-conditional Gaussians.

Autonomous Driving Object +2

Enhancing Fairness of Visual Attribute Predictors

1 code implementation7 Jul 2022 Tobias Hänel, Nishant Kumar, Dmitrij Schlesinger, Mengze Li, Erdem Ünal, Abouzar Eslami, Stefan Gumhold

The performance of deep neural networks for image recognition tasks such as predicting a smiling face is known to degrade with under-represented classes of sensitive attributes.

Attribute Fairness

Fairness by Learning Orthogonal Disentangled Representations

1 code implementation ECCV 2020 Mhd Hasan Sarhan, Nassir Navab, Abouzar Eslami, Shadi Albarqouni

We explicitly enforce the meaningful representation to be agnostic to sensitive information by entropy maximization.

Disentanglement Fairness

Deep Attention Based Semi-Supervised 2D-Pose Estimation for Surgical Instruments

1 code implementation10 Dec 2019 Mert Kayhan, Okan Köpüklü, Mhd Hasan Sarhan, Mehmet Yigitsoy, Abouzar Eslami, Gerhard Rigoll

To this end, a lightweight network architecture is introduced and mean teacher, virtual adversarial training and pseudo-labeling algorithms are evaluated on 2D-pose estimation for surgical instruments.

2D Pose Estimation Deep Attention +1

Multi-scale Microaneurysms Segmentation Using Embedding Triplet Loss

no code implementations18 Apr 2019 Mhd Hasan Sarhan, Shadi Albarqouni, Mehmet Yigitsoy, Nassir Navab, Abouzar Eslami

To enhance the discriminative power of the classification model, we incorporate triplet embedding loss with a selective sampling routine.

Classification Diabetic Retinopathy Detection +2

Learning Interpretable Disentangled Representations using Adversarial VAEs

no code implementations17 Apr 2019 Mhd Hasan Sarhan, Abouzar Eslami, Nassir Navab, Shadi Albarqouni

Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice.

Clustering Disentanglement +1

Fast 5DOF Needle Tracking in iOCT

no code implementations18 Feb 2018 Jakob Weiss, Nicola Rieke, Mohammad Ali Nasseri, Mathias Maier, Abouzar Eslami, Nassir Navab

We propose to build on its desirable qualities and present a method for tracking the orientation and location of a surgical needle.

Cannot find the paper you are looking for? You can Submit a new open access paper.