Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Eskandar, George"'
Autor:
Eskandar, George, Zhang, Chongzhe, Kaushik, Abhishek, Guirguis, Karim, Sayed, Mohamed, Yang, Bin
3D Object Detectors (3D-OD) are crucial for understanding the environment in many robotic tasks, especially autonomous driving. Including 3D information via Lidar sensors improves accuracy greatly. However, such detectors perform poorly on domains th
Externí odkaz:
http://arxiv.org/abs/2402.17562
Data efficiency, or the ability to generalize from a few labeled data, remains a major challenge in deep learning. Semi-supervised learning has thrived in traditional recognition tasks alleviating the need for large amounts of labeled data, yet it re
Externí odkaz:
http://arxiv.org/abs/2306.13585
The need for large amounts of training and validation data is a huge concern in scaling AI algorithms for autonomous driving. Semantic Image Synthesis (SIS), or label-to-image translation, promises to address this issue by translating semantic layout
Externí odkaz:
http://arxiv.org/abs/2305.09726
Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a semantic layout is used to generate a photorealistic image. State-of-the-art conditional Generative Adversarial Networks (GANs) need a huge amount of paired data to ac
Externí odkaz:
http://arxiv.org/abs/2305.09647
Autor:
Eskandar, George, Farag, Youssef, Yenamandra, Tarun, Cremers, Daniel, Guirguis, Karim, Yang, Bin
A promise of Generative Adversarial Networks (GANs) is to provide cheap photorealistic data for training and validating AI models in autonomous driving. Despite their huge success, their performance on complex images featuring multiple objects is und
Externí odkaz:
http://arxiv.org/abs/2305.09602
Autor:
Guirguis, Karim, Meier, Johannes, Eskandar, George, Kayser, Matthias, Yang, Bin, Beyerer, Juergen
Privacy and memory are two recurring themes in a broad conversation about the societal impact of AI. These concerns arise from the need for huge amounts of data to train deep neural networks. A promise of Generalized Few-shot Object Detection (G-FSOD
Externí odkaz:
http://arxiv.org/abs/2303.04958
Autor:
Guirguis, Karim, Abdelsamad, Mohamed, Eskandar, George, Hendawy, Ahmed, Kayser, Matthias, Yang, Bin, Beyerer, Juergen
Recent object detection models require large amounts of annotated data for training a new classes of objects. Few-shot object detection (FSOD) aims to address this problem by learning novel classes given only a few samples. While competitive results
Externí odkaz:
http://arxiv.org/abs/2210.05783
Autor:
Guirguis, Karim, Hendawy, Ahmed, Eskandar, George, Abdelsamad, Mohamed, Kayser, Matthias, Beyerer, Juergen
Few-shot object detection (FSOD) seeks to detect novel categories with limited data by leveraging prior knowledge from abundant base data. Generalized few-shot object detection (G-FSOD) aims to tackle FSOD without forgetting previously seen base clas
Externí odkaz:
http://arxiv.org/abs/2204.05220
Few-shot object detection (FSOD) has thrived in recent years to learn novel object classes with limited data by transferring knowledge gained on abundant base classes. FSOD approaches commonly assume that both the scarcely provided examples of novel
Externí odkaz:
http://arxiv.org/abs/2204.05072
Autor:
Eskandar, George, Marsden, Robert A., Pandiyan, Pavithran, Döbler, Mario, Guirguis, Karim, Yang, Bin
Integrating different representations from complementary sensing modalities is crucial for robust scene interpretation in autonomous driving. While deep learning architectures that fuse vision and range data for 2D object detection have thrived in re
Externí odkaz:
http://arxiv.org/abs/2203.03568