Mahmoud G. Salem

Publications

1. ICRA

   Video object segmentation using teacher-student adaptation in a human robot interaction (hri) setting

   M Siam, C Jiang, S Lu, L Petrich, M Gamal, M Elhoseiny, M Jagersand

   ICRA 2019

   Abs PDF

   Abstract—Video object segmentation is an essential task in robot manipulation to facilitate grasping and learning affordances. Incremental learning is important for robotics in unstructured environments. Inspired by the children learning process, human robot interaction (HRI) can be utilized to teach robots about the world guided by humans similar to how children learn from a parent or a teacher. A human teacher can show potential objects of interest to the robot, which is able to self adapt to the teaching signal without providing man- ual segmentation labels. We propose a novel teacher-student learning paradigm to teach robots about their surrounding environment. A two-stream motion and appearance ”teacher” network provides pseudo-labels to adapt an appearance ”stu- dent” network. The student network is able to segment the newly learned objects in other scenes, whether they are static or in motion. We also introduce a carefully designed dataset that serves the proposed HRI setup, denoted as (I)nteractive (V)ideo (O)bject (S)egmentation. Our IVOS dataset contains teaching videos of different objects, and manipulation tasks. Our proposed adaptation method outperforms the state-of-the- art on DAVIS and FBMS with 6.8% and 1.2% in F-measure respectively. It improves over the baseline on IVOS dataset with 46.1% and 25.9% in mIoU.

   Neurips

   End-To-End multi-modal sensors fusion system for urban automated driving

   Ibrahim Sobh, Loay Amin, Sherif Abdelkarim, Khaled Elmadawy, Mahmoud Saeed, Omar Abdeltawab, Mostafa Gamal, Ahmad El Sallab

   Neurips workshop 2019

   Abs PDF

   In this paper, we present a novel framework for urban automated driving based on multi-modal sensors; LiDAR and Camera. Environment perception through sensors fusion is key to successful deployment of automated driving systems, especially in complex urban areas. Our hypothesis is that a well designed deep neural network is able to end-to-end learn a driving policy that fuses LiDAR and Camera sensory input, achieving the best out of both. In order to improve the generalization and robustness of the learned policy, semantic segmentation on camera is applied, in addition to applying our new LiDAR post processing method; Polar Grid Mapping (PGM). The system is evaluated on the recently released urban car simulator, CARLA. The evaluation is measured according to the generalization performance from one environment to another. The experimental results show that the best performance is achieved by fusing the PGM and semantic segmentation.

   ICML

   Meta learning Framework for Automated Driving

   Ahmad El Sallab, Mahmoud Saeed, Omar Abdel Tawab, Mohammed Abdou

   ICML workshop 2017

   Abs PDF

   The success of automated driving deployment is highly depending on the ability to develop an efficient and safe driving policy. The prob- lem is well formulated under the framework of optimal control as a cost optimization problem. Model based solutions using traditional planning are efficient, but require the knowledge of the environment model. On the other hand, model free solutions suffer sample inefficiency and re- quire too many interactions with the environ- ment, which is infeasible in practice. Meth- ods under the Reinforcement Learning frame- work usually require the notion of a reward func- tion, which is not available in the real world. Im- itation learning helps in improving sample effi- ciency by introducing prior knowledge obtained from the demonstrated behavior, on the risk of exact behavior cloning without generalizing to unseen environments. In this paper we propose a Meta learning framework, based on data set ag- gregation, to improve generalization of imitation learning algorithms. Under the proposed frame- work, we propose MetaDAgger, a novel algo- rithm which tackles the generalization issues in traditional imitation learning. We use The Open Race Car Simulator (TORCS) to test our algo- rithm. Results on unseen test tracks show sig- nificant improvement over traditional imitation learning algorithms, improving the learning time and sample efficiency in the same time. The re- sults are also supported by visualization of the learnt features to prove generalization of the cap- tured details.

   AIxIA

   Highlighting the Importance of Reducing Research Bias and Carbon Emissions in CNNs

   Ahmed Badar, Arnav Varma, Adrian Staniec, Mahmoud Gamal, Omar Magdy, Haris Iqbal, Elahe Arani, Bahram Zonooz

   AIxIA 2021

   Abs PDF

   Convolutional neural networks (CNNs) have become commonplace in addressing major challenges in computer vision. Researchers are not only coming up with new CNN architectures but are also researching different techniques to improve the performance of existing architectures. However, there is a tendency to over-emphasize performance improvement while neglecting certain important variables such as simplicity, versatility, the fairness of comparisons, and energy efficiency. Overlooking these variables in architectural design and evaluation has led to research bias and a significantly negative environmental impact. Furthermore, this can undermine the positive impact of research in using deep learning models to tackle climate change. Here, we perform an extensive and fair empirical study of a number of proposed techniques to gauge the utility of each technique for segmentation and classification. Our findings restate the importance of favoring simplicity over complexity in model design (Occam's Razor). Furthermore, our results indicate that simple standardized practices can lead to a significant reduction in environmental impact with little drop in performance. We highlight that there is a need to rethink the design and evaluation of CNNs to alleviate the issue of research bias and carbon emissions.